Conference Programme – Day 1

Day 1

Wednesday, 13 May 2026  

09:30 - 11:00

Opening Ceremony

11:00 - 11:20

Coffee Break

11:20 - 13:00

Session O1: Dialogue, Conversational Systems, Chatbots, Human-Robot Interaction - Room 1

11:20 - 11:40

Beyond Generic Responses: Target-Aware Strategies for Countering Hate Speech Yen-Yu Chang1, Daryna Dementieva1, Alexander Fraser2 1Technical University of Munich, 2Ludwig-Maximilians-Universität München

11:40 - 12:00

Topic-Initiator: A Proactive Chatbot with Personalized Topic RAG for Enhancing Willingness to Converse Kazuya Matsuo1, Atsushi Otsuka2, Narichika Nomoto3, Makoto Nakatsuji1 1NTT, 2NTT Corporation, 3NTT Corporration

12:00 - 12:20

CoachLah: A Singlish–English Parallel Corpus of Health Coaching Conversations with Behavior Goal Annotations Iva Bojic1, Mathieu Ravaut2, Stephanie Hilary Xinyi Ma1, Doreen Tan3, Andy Hau Yan Ho1, Andy Khong1 1Nanyang Technological University, 2Abu Dhabi Investment Authority, 3National University of Singapore

12:20 - 12:40

Faithful Medical Dialogue Generation Using Homo-Heterogeneous Exemplar-based In-Context Knowledge Grounding Priyanshu Priya, Hardik Goyal, Asif Ekbal Indian Institute of Technology Patna

12:40 - 13:00

Investigating Proactivity in Multimodal Task-Guidance Dialogues Sofia Brenna1, Elisabetta Jezek2, Matthias Kraus3, Bernardo Magnini4 1FBK, Unibz, 2University of Pavia, 3Augsburg University, 4FBK

11:20 - 13:00

Session O2: Interpretability, Explainability I - Room 2

11:20 - 11:40

REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs Liran Cohen, Yaniv Nemcovesky, Avi Mendelson Technion – Israel Institute of Technology

11:40 - 12:00

Why So Separate: Analyzing In-Context Learning from a Vector Space Perspective Tobias Kalmbach1 and Sandipan Sikdar2 1L3S Research Center, Leibniz University Hannover, 2Leibniz University Hannover

12:00 - 12:20

Explaining Explanations: Interpretability Methods for Discourse Analysis of Transformer Attention Maps Louis Escouflaire1, Jérémie Bogaert2, Antonin Descampe2, Cédrick Fairon3, Francois-Xavier Standaert4 1Massachusetts Institute of Technology, 2UCLouvain, 3Université catholique de Louvain, CENTAL, 4UCL Crypto Group

12:20 - 12:40

TempPerturb-Eval: On the Joint Effects of Internal Temperature and External Perturbations in RAG Robustness Yongxin Zhou1, Philippe Mulhem2, Didier Schwab3 1Université Grenoble Alpes, 2LIG-CNRS, 3Univ. Grenoble Alpes

12:40 - 13:00

Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics Iker García-Ferrero, David Montero, Roman Orus Multiverse Computing

11:20 - 13:00

Session O3: Document Classification, Information Retrieval and Cross-lingual Retrieval - Room 3

11:20 - 11:40

To Predict or Not to Predict? Towards Reliable Uncertainty Estimation in the Presence of Noise Nouran Khallaf and Serge Sharoff University of Leeds

11:40 - 12:00

An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took "Use of Practical AI in Digital Libraries" Seriously? Jennifer D'Souza1, Sameer Sadruddin1, Maximilian Kaehler2, Andrea Salfinger3, Luca Zaccagna3, Francesca Incitti3, Lauro Snidaro3, Osma Suominen4 1TIB Leibniz Information Centre for Science and Technology, 2Deutsche Nationalbibliothek, 3University of Udine, 4National Library of Finland

12:00 - 12:20

A Historical Database for the Study of Obstruent-Lateral Palatalization in Ibero-Romance Andrea García Covelo LMU Munich

12:20 - 12:40

Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients Oumaima El Khettari1, Virgile Barthet2, Guillaume Hocquet3, Joconde Weller3, Emmanuel Morin4, Pierre Zweigenbaum2 1Nantes Université - LS2N, 2LISN, CNRS, Université Paris-Saclay, 3Direction of Medical Information, Prospects and Data Sciences, Hôpitaux Paris Saint-Joseph and Marie-Lannelongue, Paris, Franc, 4LS2N UMR CNRS 6004

12:40 - 13:00

HistoriQA-ThirdRepublic: Multi-Hop Question Answering Corpus for Historical Research, Parliamentary Debates from the French Third Republic (1870-1940) Aurelien Pellet1, Marie Puren2, Julien PEREZ3 1LRE - EPITA, EPITECH, 2LRE (EPITA), 3LRE, EPITA

11:20 - 13:00

Session O4: Evaluation, Validation, Quality Assurance and Benchmarking Methodologies - Room 4

11:20 - 11:40

Assessing the Political Fairness of Multilingual LLMs: A Case Study Based on a 21-Way Multiparallel EuroParl Dataset Paul Lerner1 and François Yvon2 1Sorbonne Université, CNRS, ISIR, 2ISIR CNRS & Sorbonne Université

11:40 - 12:00

AfriStereo: A Culturally Grounded Dataset for Evaluating Stereotypical Bias in Large Language Models Yann Le Beux1, Oluchi Audu1, Oche Ankeli1, Dhananjay Balakrishnan2, Melissah Weya1, Marie Ralaiarinosy1, Ignatius Ezeani3 1YUX Design, 2Stanford University, 3Lancaster University

12:00 - 12:20

Judging Instruction Responses in a Low-Resource Language: A Case Study on Basque David Ponce1, Harritxu Gete1, Thierry Etchegoyhen1, Irune Zubiaga2, Aitor Soroa3 1Vicomtech, 2EHU/UPV, 3HiTZ Center - Ixa, University of the Basque Country UPV/EHU

12:20 - 12:40

Appeal, Align, Divide? Stance Detection for Group-Directed Messages in German Parliamentary Debates Ines Rehbein1, Maris Buttmann2, Julian Schlenker1, Simone Paolo Ponzetto1 1University of Mannheim, 2Mannheim University

12:40 - 13:00

BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models Thura Aung1, Jann Montalan2, Jian Ngui2, Peerat Limkonchotiwat3 1King Mongkut's Institute of Technology Ladkrabang, 2AI Singapore; National University of Singapore, 3AI Singapore

11:20 - 13:00

Session P1.1: Applications: Datasets and Benchmarks - Poster Area

Report-based Recommendations for Policy Making and Agency Operations: Dataset and LLM Evaluation Aleksandra Edwards, Thomas Edwards, Jose Camacho-Collados, Alun Preece Cardiff University

ConceptKT: A Benchmark for Concept-Level Deficiency Prediction in Knowledge Tracing Yu-Chen Kang1, Yu-Chien Tang2, An-Zi Yen2 1National Yang Ming Chiao Tung Universit, 2National Yang Ming Chiao Tung University

Open-access Dataset on Acceptability Ratings of Korean Clausal Constructions by Humans and GPT Models Gyu-Ho Shin1, Soo-Hwan Lee2, Chanyoung Lee3 1University of Illinois Chicago, 2Gyeongsang National University, 3Konkuk University

Talk2Ref: A Dataset for Reference Prediction from Scientific Talks Frederik Broy1, Maike Züfle1, Jan Niehues2 1Karlsruhe Institute of Technology, 2Karlsruhe Institut of Technology

MuSaG: A Multimodal German Sarcasm Dataset with Full-Modal Annotations Aaron Scott1, Maike Züfle2, Jan Niehues3 1Karlsruher Institut für Technologie, 2Karlsruhe Institute of Technology, 3Karlsruhe Institut of Technology

Icelandic Math Eval: A Competitive Mathematics Benchmark for Large Language Models Hafsteinn Einarsson, Jökull Haraldsson, Ívar Derayat, Sigrún Lund, Benedikt Magnússon University of Iceland

MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models Hafsteinn Einarsson University of Iceland

J-ClinicalBench: A Benchmark for Evaluating Large Language Models on Practical Clinical Tasks in Japanese Seiji Shimizu1, Tomohiro Nishiyama1, HISADA Shohei1, Yamato Himi1, Shoko Wakamiya2, Yuki Yanagisawa3, Masami Tsuchiya3, Satoko Hori3, Eiji ARAMAKI4 1Nara Institute of Science and Technology, 2NAIST, 3Keio University, 4NAIST, Japan

Is One Dataset Enough for Evaluation? Studying Generalizability of Automated Essay Scoring Models Sohaila Eltanbouly, Marwan Sayed, Tamer Elsayed Qatar University

HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings Rasmus Jensen1, Giovanni Rizzi2, Rasmus Tjalk-Bøggild2, Alexandre Iolov2, Mike Zhang3, Johannes Bjerva4 1Aalborg university, 2Alipes ApS, 3University of Copenhagen, 4Department of Computer Science, Aalborg University

UniSkill: A Dataset for Matching University Curricula to Professional Competencies Nurlan Musazade1, József Mezei1, Mike Zhang2 1Åbo Akademi University, 2University of Copenhagen

A Dataset for Evaluating ASR on Specialized Vocabulary Emily Haubert Klering1, Eduardo Cortes1, Tatjana Chernenko2, Mariana Vargas Trarbach1, Gabriel de Oliveira Ramos1, Sandro José Rigo1, Maitê Dupont2, Ana Treichel Vianna2, Gabriela Krause dos Santos1, Vinicius Meirelles Pereira2, Denis de Araujo1, Rafael Kunst1 1UNISINOS, 2SAP SE

SommBench: Assessing Sommelier Expertise of Language Models William Brach1, Tomas Bedej2, Jacob Nielsen3, Jacob Pichna2, Juraj Bedej2, Eemeli Saarensilta2, Julie Dupouy2, Gianluca Barmina3, Andrea Blasi Núñez3, Peter Schneider-Kamp3, Kristian Koštál1, Michal Ries1, Lukas Galke Poech3 1Slovak Technical University, 2sommify, 3University of Southern Denmark

CzechDocs: A Multiway Parallel Dataset of Formatted Documents for Minority Languages in Czechia Josef Jon1 and Ondrej Bojar2 1Charles University, 2Charles University, MFF UFAL

11:20 - 13:00

Session P1.2: Applications: LLMs - Poster Area

An LLM-Based Assistant for Debt Waiver Court Procedures Lluis Padro1, Daniel Ferrés2, Roser Saurí3, Mireia Artigot2 1Universitat Politecnica de Catalunya, 2Universitat Pompeu Fabra, 3Process Talks, S.L.

Enhancing Clinical Trial Analysis through Large Language Models for Multi-Evidence Natural Language Inference Shobanapriyan Chandrasegaran and Amal Htait Aston University

A Systematic Comparison of Large Language Models for Data Annotation in NER Tasks Muhammad Uzair Ul Haq1, Davide Rigoni2, Alessandro Sperduti3 1Amajor SpA SB, 2University of Padua, Fondazione Bruno Kessler, 3University of Padova

Toward Generalized Cross-Lingual Hateful Language Detection with Web-Scale Data and Ensemble LLM Annotations Dang Dang1, Jelena Mitrovic2, Michael Granitzer2 1Passau University, 2University of Passau

Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian Mobina Mehrazar1, Mohammad Amin Yousefi2, Parisa Beygi3, Behnam Bahrak4 1mobinamehrazar@ut.ac.ir, 2m.amin.yousefi@ut.ac.ir, 3The University of British Columbia, 4Tehran Institute for Advanced Studies (TEIAS)

Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study Hawau Olamide Toyin1, Samar Mohamed Magdy2, Hanan Aldarmaki3 1Mohamed Bin Zayed University of Artificial Intelligence, 2ubc.ca;, 3MBZUAI

Automatic Suggestions of Supplements in the Herculaneum Papyri: Language Models and RESTful API Angelo Mario Del Grosso1, Gabriele Giannessi2, Simone Zenzaro3, Federico Boschetti4 1Cnr-Istituto di Linguistica Computazionale "Antonio Zampolli" (CNR-ILC), 2University of Pisa at Pisa, 3CNR-ILC, 4ILC-CNR

Designing LLM Agents for User-Centered Language Service Selection Ryoichiro Ogawa, Donghui Lin, Fumito Uwano Okayama University

User Profiling for Specification-Sensitive Recommendations with Large Language Model Prompting Chih-Yu Chien1, An-Zi Yen2, Hen-Hsen Huang3, Hsin-Hsi Chen1 1National Taiwan University, 2National Yang Ming Chiao Tung University, 3Institute of Information Science, Academia Sinica

Comparing Traditional and LLM-based Approaches for Automated Scoring of Dutch Writing Products Joni Kruijsbergen and Orphee De Clercq LT3, Ghent University

``Decode the Law": Towards Legal Text Simplification with Large Language Models Mohammed Rabbani1, Subhadeep Roy2, Sayantan Mitra3, Tulika Saha1 1IIIT Bangalore, 2University of Technology Nuremberg, 3Accenture Technology Labs

11:20 - 13:00

Session P1.3: Applications - Poster Area

CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation Yiran Ma1, Yuxiao Ye2, Huiyuan Xie2 1Beijing University of Posts and Telecommunications, 2Tsinghua University

Neural Network-assisted Analysis of Tube Vocal Tract Models Runhui Song1, Johan Sjons1, Axel Ekstrom2 1Department of Linguistics and Philology, Uppsala University, 2Speech, Music & Hearing, KTH Royal Institute of Technology

Central Kurdish TTS and Its Application in Speech to Text Translation Mohammad Mohammadamini1, Meysam Shamsi2, Marie Tahon3 1Le Mans University, 2LIUM, Le Mans University, 3LIUM / Le Mans University

QuALA-NL: Question & Answer with Legal Attribution in Dutch Romy van Drie1, Roos Bakker2, Daan Di Scala3, Maaike de Boer1 1TNO, 2TNO, University of Leiden, 3TNO, Utrecht University

SouDeC: Source Detection and Classification in Czech Jirí Mírovský and Barbora Hladka Charles University

Frame Semantic Patterns for Identifying Underreporting of Notifiable Events in Healthcare: The Case of Gender-Based Violence Lívia Dutra1, Arthur Lorenzi2, Lais Berno2, Franciany Campos2, Karoline Biscardi3, Kenneth Brown2, Marcelo Viridiano4, Frederico Belcavello2, Ely Matos5, Olivia Guaranha6, Erik Santos6, Sofia Reinach6, Tiago Timponi Torrent2 1Gothenburg University, 2Federal University of Juiz de Fora, 3Federal University of Minas Gerais, 4Case Western Reserve University, 5UFJF - Federal University of Juiz de Fora, 6Vital Strategies Brasil

PrePPER: A Preference Pattern-based Profiling Framework for Explainable Recommendation Taisuke Usumi, Akiko Masaki, Sanae Muramatsu, Akira Sakamoto, Takeharu Eda NTT Software Innovation Center

Evaluating the Impact of Source Diversity for RAG in Historical Research Ruhi Mahadeshwar1, Andreas van Cranenburgh1, Tommaso Caselli2, Malvina Nissim1 1University of Groningen, 2Rijksuniversiteit Groningen

Automatic Essay Scoring and Feedback Generation in Basque Language Learning Ekhi Azurmendi1, Xabier Arregi2, Oier Lopez de Lacalle3 1HiTZ Center - Ixa, University of the Basque Country UPV/EHU, 2HiTZ center. University of the Basque Country/Euskal Herriko Unibertsitatea, 3University of the Basque Country

Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech Fabian Retkowski1 and Alexander Waibel2 1Karlsruhe Insitute of Technology (KIT), 2Carnegie Mellon

High-Order Question Generation in a Multilingual Educational Context Suna Uçar1, Itziar Aldabe1, Nora Aranberri1, Orphee De Clercq2 1University of the Basque Country (UPV/EHU), 2LT3, Ghent University

From Print to Digital and beyond: The Retrodigitization of a Historical Dictionary of Italian as a Hybrid Lexical Resource Marco Biffi1, Sebastiana Cucurullo2, Manuel Favaro2, Elisa Guadagnini2, Simonetta Montemagni3, Eva Sassolini2 1University of Florence & Accademia della Crusca, 2CNR-ILC, 3Istituto di Linguistica Computazionale "Antonio Zampolli"

Learning through News: Bridging the Gap between Algorithmic Recommendation and Human Curation Florian Debaene1, Loic De Langhe1, Orphee De Clercq2, Veronique Hoste2 1Ghent University, 2LT3, Ghent University

MaskedVerbalizer: Automatic Verbalizer Construction for Few-Shot Text Classification in Low-Resource Right-to-Left Languages Faizad Ullah1, Furqan Sikandar2, Areeba Waqar3, Faizan Ali4, Muhammad Sohaib Ayub5, Mubashar Mushtaq6, Asim Karim7 1Department of Computer Science, Lahore University of Management Sciences (LUMS), 2Forman christian college and university, 3FCCU, 4Forman Christian College University, 5Data Science Institute, University of Galway, 6FC College - A Chartered University, 7Lahore University of Management Sciences (LUMS)

RBR: RAG-Based Open-Domain Question Answering Using a Ranking Approach to Document Retrieval Priyatam Naravajhula and Vincent Ng university of Texas at Dallas

Sentence-Level Back-Transliteration of Romanized Indian Languages: Performance Analysis and Challenges Saurabh Kumar1, Dhruvkumar Kakadiya1, Sanasam Ranbir Singh2, Sukumar Nandi1 1Indian Institute of Technology Guwahati, 2Indian Institute of Technology

Cross-Corpus CEFR Classification through Artificial Learners Perplexities bernardo stearns1, John Mccrae2, Thomas Gaillat3 1National University of Ireland, 2University of Galway, 3university rennes 2

11:20 - 13:00

Session P1.4.1: Digital Humanities I - Poster Area

CorpusClues: Scalable Unsupervised Similarity Search for Historical Texts Using MinHash-LSH Paulien Lemay, Klaas Bentein, Els Lefever Ghent University

BenCSSmark: Making the Social Sciences Count in LLM Research Arnault Chatelain1, Etienne Ollion1, Qianwen Guan2, Diandra Fabre3, Lorraine Goeuriot4, emile chapuis5, Abdelkrim Beloued5, Marie Candito6, Nicolas Hervé5, Didier Schwab7 1CREST (Ecole Polytechnique, ENSAE, CNRS), 2LLF (Université Paris Cité and CNRS), 3Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 4LIG, Université Grenoble Alpes, 5INA, 6LLF, Université Paris Cité, 7Univ. Grenoble Alpes

Predicting Topic (Co-)Occurrence Using Topic Networks Built from the Project Gutenberg Corpus Bhuvanesh Verma1 and Alexander Mehler2 1University of Frankfurt, 2Goethe-University Frankfurt am Main

AraHopeCorpus: Annotation Guidelines and Dataset for Hope Speech in Arabic Social Media Crisis Discourse Esra'a Sharqawi1 and Wajdi Zaghouani2 1Hamad Bin Khalifa University, 2Northwestern University Qatar

Cohesion-6K: An Arabic Dataset for Analyzing Social Cohesion and Conflict in Online Discourse Aisha Al-Athba1 and Wajdi Zaghouani2 1Hamad Bin Khalifa University, 2Northwestern University Qatar

Reference-free Evaluation at Inference for NER/NEL over OCRed Historical Texts Tien-Nam Nguyen1, Adam Jatowt2, Ahmed Hamdi3, Mickael Coustaty4, Thi Hong Hanh TRAN5, Antoine Doucet6 1L3i, 2University of Innsbruck, 3IRIT, University of Toulouse, 4L3i laboratory - La Rochelle Université, 5Arkhn, 6University of La Rochelle

Echoes of the Troubadours: A Corpus of Troubadour Poetry for Stylometric Analysis and Authorship Attribution Loic De Langhe1, Orphee De Clercq2, Veronique Hoste2 1Ghent University, 2LT3, Ghent University

Gretino: A Greek and Latin Dataset to Benchmark Retrieval Systems in Classical Languages Hawau Olamide Toyin1, Federico Iezzi2, Elia Scapini2, Giulio Federico3, Giovanni Puccetti4 1Mohamed Bin Zayed University of Artificial Intelligence, 2University of Modena and Reggio Emilia, 3Institute of Science and Technologies of Information, 4information Science and Technologies Institute "A. Faedo"

A Recipe for Adapting Multilingual Embedders to OCR-Error Robustness and Historical Texts Andrianos Michail1, Stylianos Psychias2, Juri Opitz1, Simon Clematide1 1University of Zurich, 2MSc Student - University of Zurich

Phrase-Level Segmentation on Medieval Corpora for Aligning Multilingual Texts Lucence Ing1, Matthias Gille Levenson2, Carolina Macedo3 1Inria, 2ENS de Lyon, 3École Nationale des chartes

11:20 - 13:00

Session P1.4.2: Digital Humanities II - Poster Area

RAGE: Roman and Greek Emotions Frederick Riemenschneider, Jonathan Geiger, Thomas Kuhn-Treichel, Anette Frank Heidelberg University

From Variance to Invariance: Qualitative Content Analysis for Narrative Graph Annotation Junbo Huang1, Max Weinig1, Ulrich Fritsche1, Ricardo Usbeck2 1University of Hamburg, 2Leuphana University Lueneburg

A Dataset of Historical Medical Periodicals Annotated with Textual Genre Vera Danilova and Sara Stymne Uppsala University

Preserving Endangered Linguistic Heritage: Developing a Corpus for the Study of Contact-induced Changes in Corfioto Giorgio Maria Di Nunzio1 and Georgios Vardakis2 1University of Padua, 2Ionian University

To Eat and beyond: A FrameNet-Inspired Annotation of Food and Its Uses over Time Teresa Paccosi1, Gauri Bhagwat2, Marieke van Erp3 1KNAW, 2DHLab, KNAW, 3KNAW Humanities Cluster

To Overfit or Not to Overfit? An Evaluation of HTR Workflow on 17Th-18Th Century French Corpus Marine Tiger Sorbonne-Université

Automatic Segmentation of Classical Tibetan Texts into Autochthonous and Allochthonous Regions Guy Bilitski1, Lev Shechter2, Sonam Jamtsho3, Nir Marciano2, Nicola Bajetta3, Rebecca Sunden3, Omri Drori2, Kai Golan Hashiloni2, Orr Zwebner2, Asaf Shina2, Orna Almogi3, Dorji Wangchuk3, Kfir Bar2 1RUNI, 2Reichman University, 3University of Hamburg

RespondeoQA: A Benchmark for Bilingual Latin-English Question Answering Marisa Hudspeth1, Patrick Burns2, Brendan O'Connor1 1University of Massachusetts Amherst, 2New York University

Transformer-Enabled Diachronic Analysis of Vedic Sanskrit: Neural Methods for Quantifying Types of Language Change Ananth Hariharan1 and David R. Mortensen2 1University of Illinois Urbana-Champaign, 2Language Technologies Institute, Carnegie Mellon University

Ithaca Revisited: Benchmarking a Domain-Specific Model for Epigraphy in the Age of LLMs Alessandro Locaputo1, Andrea Brunello1, Nicola Saccomanno1, Paraskevi Platanou2, Giuseppe Serra1 1University of Udine, 2National and Kapodistrian University of Athens

11:20 - 13:00

Session P1.5: Simplification, Accessibility - Poster Area

CEFR Level Prediction for Short Russian L2 Texts: Evaluating Classifiers and Instruction-Based LLMs Anna Glazkova1, Antonina Laposhina2, Dmitry Morozov3 1University of Tyumen, 2Pushkin State Russian Language Institute, 3Novosibirsk State University

Evaluation of Document-Level Text Simplification in Japanese Iori Yamashita, Hikari Tanaka, Hajime Kiyama, Kexin Bian, Zhousi Chen, Mamoru Komachi Hitotsubashi University

Parallel Corpus Filtering Based on Semantic Similarity and Surface Dissimilarity for Japanese Text Simplification with LLMs Daisuke Maekawa1, Tomoyuki Kajiwara2, Takashi Ninomiya1 1Ehime University, 2Ehime University / The University of Osaka

A Multilingual Human Annotated Corpus of Original and Easy-to-Read Texts to Support Access to Democratic Participatory Processes Verena Riegler1, Stefan Bott2, Horacio Saggion3, Almudena Rascón Alcaina4, Nouran Khallaf5 1capito.ai, 2Universitat Pompe Fabra, 3Universitat Pompeu Fabra, 4Plena Inclusión Madrid, 5University of Leeds

Proffiliadur: Welsh Language Text Profiling Toolkit Nicolás Gutiérrez-Rolón, Jonathan Davies, Tomos Williams, Dawn Knight, Fernando Alva-Manchego Cardiff University

Recovering Registers from Leveled Wordlists Yo Ehara Tokyo Gakugei University

11:20 - 13:00

Session P1.6: Infrastructures, Policy and Legal Issues I - Poster Area

Fill-in-the-Blanks: Automatic Generation and Evaluation of Language Models' Pseudonyms for English and Swedish Texts Maria Irena Szawerna1 and Jacob Suchardt2 1University of Gothenburg, 2Leipzig University

Integrating Services, Platforms and Resources into a National Infrastructure Cluster for FAIR Language and Cultural Data Giulia Pedonese1, Daniele Melaccio2, Michele Mallia3, Monica Monachini4, Francesca Frontini5, Valeria Quochi6, Fahad Khan7, Angelo Mario Del Grosso8, Federico Boschetti9, Riccardo Del Gratta9 1CNR - Istituto di Linguistica Computazionale "Antonio Zampolli", 2Istituto di Linguistica Computazionale ILC-CNR, 3Istituto di Linguistica Computazionale "A. Zampolli" - CNR Area di Pisa, 4Institute of Computational Linguistics "A. Zampolli" - CNR, 5Istituto di Linguistica Computazionale "A. Zampolli" - ILC Consiglio Nazionale delle Ricerche - CNR, 6Consiglio Nazionale delle Ricerche. Istituto di Linguistica Computazionale "A. Zampolli", 7Istituto di Linguistica Computazionale "Antonio Zampolli", CNR, 8Cnr-Istituto di Linguistica Computazionale "Antonio Zampolli" (CNR-ILC), 9ILC-CNR

Common European Language Data Space: Development, Current Status, and Future Perspectives Stelios Piperidis1, Penny Labropoulou2, Dimitrios Galanis3, Khalid Choukri4, Andrejs Vasiljevs5, Mitos Deligiannis1, Katerina Gkirtzou6, Dimitris Gkoumas1, Athanasia Kolovou7, Leon Voukoutis2, Kanella Pouli1, Maria Giagkou8, Maria Gavriilidou2, Katrin Marheinecke9, Elena Leitner9, Simon Ostermann10, Stefania Raccioppa9, Kossay Talmoudi11, Victoria Arranz11, Valérie Mapelli11, Helene Mazo12, Fernanda González Campo11, Shi Yu11, Aivars Be¯rzin¸s?5, Andis Lagzdin¸s?5, Georg Rehm9 1Athena RC/ILSP, 2ILSP / Athena RC, 3Institute for Language and Speech Processing, Athena Research Center, 4ELRA/ELDA, 5Tilde, 6ILSP/Athena Research Center, 7National and Kapodistrian University of Athens, 8ILSP/ATHENA RC, 9DFKI, 10German Research Center for Artificial Intelligence (DFKI), 11ELDA, 12ELRA

Euskorpora: A Strategic Framework for Digital Sovereignty and Linguistic Inclusion of Basque in the Era of AI Victoria Arranz, Sara Arregi, Leire Barañano, Aitor García-Pablos Euskorpora

Automating FAIRness: A FAIRification Tool within the Language Resources Infrastructure Daniele Melaccio1 and Monica Monachini2 1Istituto di Linguistica Computazionale ILC-CNR, 2Institute of Computational Linguistics "A. Zampolli" - CNR

FIBER: Factual Inference Bias Evaluation Resource Evren Ayberk Munis1, Deniz Yilmaz2, Arianna Muti3, Cagri Toraman2 1Politecnico Di Torino, 2Middle East Technical University, Computer Engineering Department, 3Bocconi University

EthiQuest: LLM-Powered Ethical Questionnaire Generation for Research Review ishank kapania, Radhika Mamidi, Rahul Mishra IIIT-H | International Institute of Information Technology - Hyderabad

13:00 - 14:30

Lunch Break

14:30 - 15:15

Keynote Speaker: Nancy Chen - Room 1

15:15 - 15:20

Short Break (5mn)

15:20 - 17:00

Session O5: Inference, Reasoning, Question Answering I - Room 1

15:20 - 15:40

NegNLI-BR: A Brazilian Portuguese Benchmark for Negation in Natural Language Inference Matheus Westhelle1 and Viviane Moreira2 1Universidade Federal do Rio Grande do Sul, 2Institute of Informatics - UFRGS

15:40 - 16:00

SWE-QA: A Dataset and Benchmark for Complex Code Understanding Laila ELKOUSSY and Julien PEREZ LRE, EPITA

16:00 - 16:20

Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA Rishabh Maheshwary1, Masoud Hashemi2, Khyati Mahajan1, Shiva Krishna Reddy Malay1, sai rajeswar mudumba3, Sathwik Tejaswi Madhusudhan4, Spandana Gella5, Vikas Yadav1 1ServiceNow, 2ServiceNow, PLATO, 3university de montreal, 4Service Now, 5Amazon Alexa AI

16:20 - 16:40

Information Asymmetry across Language Varieties: A Case Study on Cantonese-Mandarin and Bavarian-German QA Renhao Pei1, Siyao Peng2, Verena Blaschke2, Robert Litschko2, Barbara Plank2 1University of Turku, 2LMU Munich

16:40 - 17:00

FRASE: Frame-based Structured Representations for Generalizable SPARQL Query Generation Papa Abdou Karim Karou Diallo1 and Amal Zouaq2 1Polytchnique Montreal, 2Polytechnique Montreal

15:20 - 17:00

Session O6: Information Extraction and Text Mining I - Room 2

15:20 - 15:40

Representing Multimodality in Terminology Resources Federica Vezzani University of Padua

15:40 - 16:00

EPOP: A Benchmark Corpus for Assessing NLP Models on Structured Information Extraction in Plant Health Claire Nedellec1, Marine Courtin2, Xinzhi Yao3, Marie Grosdidier1, Isabelle Pieretti4, Sandy Duperier1, Robert Bossy5 1INRAE, 2LPP (CNRS) - Paris 3 Sorbonne Nouvelle, 3Huazhong Agricultural University, 4CIRAD, 5Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement

16:00 - 16:20

ReTaT: A Unified Benchmark for Relation Extraction across Text and Table Mohamed Ettaleb1, Thibault Ehrhart2, Nathalie Aussenac-Gilles3, Yoan Chabot4, Mouna Kamel5, Véronique MORICEAU6, Raphael Troncy2, Fanfu Wei2 1Institut de Recherche en Informatique de Toulouse, 2EURECOM, 3CNRS - IRIT, 4Orange, 5IRIT, 6IRIT, Université de Toulouse

16:20 - 16:40

LitTx: A New Treatment Relation Extraction Dataset Yuhang Jiang1, Md Sultan Al Nahian2, Li Hao Richie Xu1, Rani Chikkanna1, Ramakanth Kavuluru1 1University of Kentucky, 2Pennsylvania State University Harrisburg

16:40 - 17:00

LegitimNarrate: A Dataset for Analyzing Legitimation Mechanisms in Crowdfunding Narratives Asmaa Lagrid1, Sebastien Fournier2, Benedicte ALDEBERT1, Ali Ghods3, Daisy Bertrand3, Gael Leboeuf3 1Aix-Marseille university (amu), 2LSIS, 3Aix-Marseille university

15:20 - 17:00

Session O7: Language Modeling and LRs I - Room 3

15:20 - 15:40

A Fine-tuned ASR Model for Historical American Dialect Recordings Steven Coats University of Oulu

15:40 - 16:00

A Comprehensive Full-Form Lexicon for Arabic NLP and Speech Technology Yannis Haralambous1 and Jack Halpern2 1IMT Atlantique & CNRS LabSTICC, 2The CJK Dictionary Institute

16:00 - 16:20

MzansiText and MzansiLM: An Open Corpus and Decoder-Only Language Model for South African Languages Anri Lombard, Temi Aina, Ethan Wolff, Elan Norvick, Sbonelo Gumede, Simbarashe Mawere, Francois Meyer, Jan Buys University of Cape Town

16:20 - 16:40

Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models Stephan Oepen1, Nikolay Arefyev2, Mikko Aulamo3, Marta Bañón4, Maja Buljan5, Laurie Burchell6, Lucas Charpentier7, Pinzhen Chen8, Mariia Fedorova2, Ona de Gibert3, Barry Haddow9, Jan Hajic10, Jindrich Helcl2, Andrey Kutuzov2, Veronika Laippala11, Zihao Li3, Bhavitvya Malik12, Vladislav Mikhailov2, Amanda Myntti11, Dayyán O'Brien12, Lucie Polakova10, Gema Ramírez-Sánchez13, Janine Siewert3, Pavel Stepachev14, Joerg Tiedemann3, Teemu Vahtola3, Dusan Varis15, Fedor Vitiugin16, Jaume Zaragoza13 1Universitetet i Oslo, 2University of Oslo, 3University of Helsinki, 4Prompsit SL, 5Language Technology Group (LTG), University of Oslo, 6Common Crawl Foundation, 7Language Technology Group, University of Oslo, 8Queen's University Belfast, 9University of Edinburgh & Aveni, 10Charles University, 11University of Turku, 12University of Edinburgh, 13Prompsit Language Engineering, 14The University of Edinburgh, 15Charles University, Institute of Formal and Applied Linguistics, 16Universitat Pompeu Fabra

16:40 - 17:00

Generation of Instruction and Preference Dataset for Improving Japanese Instruction Following in LLMs Kei Moriyama1, Takashi Kodama2, Kouta Nakayama2 1The University of Tokyo, 2National Institute of Informatics

15:20 - 17:00

Session O8: Less-Resourced/Endangered/Less-studied Languages - Room 4

15:20 - 15:40

Adapting Pretrained Models to Endangered Languages in Japan: A Comparative Study on Ryukyuan and Ainu Speech Recognition Kohei Matsuura1, Takanori Ashihara2, Tatsuya Kawahara1 1Kyoto University, 2NTT Corporation

15:40 - 16:00

Prerequisites for Advancing Automatic Speech Recognition in Breton Morgan Grobol1, Alice Millour2, Wassim Zemouri3, Yuna Drapier4, Mélanie Jouitteau5 1Université Paris Nanterre, 2Université Paris 8 Vincennes Saint-Denis, 3École supérieure en informatique 08 Mai 1945 - Sidi Bel Abbès -, 4Dastum, 5CNRS

16:00 - 16:20

Integrating TEI, NER/NEL, Textometry, and Linked Data for a Semantically Enriched Interview Corpus Ranka Stankovic1, Tamara Vucenovic2, Biljana Rujevic3, Milica Ikonic Nešic4, Mihailo Škoric5 1University of Belgrade - Faculty of Mining and Geology, 2University Metropolitan, Faculty of Management, 3University of Belgrade, Faculty of Mining and Geology, 4University of Belgrade, Faculty of Philology, 5University of Belgrade Faculty of Mining and Geology

16:20 - 16:40

Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages Edward Bayes1, Israel Abebe Azime2, Jesujoba Alabi2, Jonas Kgomo3, Tyna Eloundou4, Elizabeth Proehl4, Kai Chen4, Imaan Khadir3, Naome Etori5, Shamsuddeen Hassan Muhammad6, Choice Mpanza7, Igneciah Pocia Thete7, Dietrich Klakow2, David Ifeoluwa Adelani8 1General Purpose, 2Saarland University, 3Equiano Institute, 4OpenAI, 5University of Minnesota - Twin Cities, 6Bayero University, Kano, 7University of South Africa, 8McGill University / MILA

16:40 - 17:00

Dialectal Filtering: Synthesizing Kurdish Corpora for Low-Resource Varieties by Utilizing "Noise" in Large Textual Data Christian Schuler1, Raman Ahmad2, Anrán Wáng1, Daniil Gurgurov3, Timo Baumann4, Simon Ostermann5, Josef van Genabith3 1Saarland University, 2HAW Hamburg, Department Informatik, 3DFKI, 4Ostbayerische Technische Hochschule Regensburg, 5German Research Center for Artificial Intelligence (DFKI)

15:20 - 17:00

Session P2.1.1: Corpora and Treebanks I - Poster Area

HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection Luke Patterson, Li Wang, Adam Faulkner Capital One

CorEGe-PT: Compiling a Large Corpus of Academic Texts in~Portuguese Tanara Zingano Kuhn1, José Matos2, Bruno Neves3, Daniela Pereira4, Elisabete Cação4, Ivo Simões2, Jacinto Estima2, Delfim Leão5, Hugo Goncalo Oliveira6 1Research Centre for General and Applied Linguistics (CELGA-ILTEC), University of Coimbra, 2University of Coimbra, CISUC/LASI, Department of Informatics Engineering, 3Universidade de Coimbra, Biblioteca Geral, 4Independent Researcher, 5University of Coimbra, 6CISUC, DEI, University of Coimbra

SLURP-TN : Resource for Tunisian Dialect Spoken Language Understanding Haroun Elleuch1, Salima Mdhaffar2, Yannick Estève3, Fethi Bougares4 1Elyadata - LIA, 2LIA - University of Avignon, 3LIA - Avignon Université, 4LIUM- Le Mans Université

Constructing and Annotating Historical Multilingual Parallel Text Collections on the TEITOK Platform Maarten Janssen1, Anna Jouravel2, Piroska Lendvai3 1UFAL, Charles University, LINDAT/CLARIAH-CZ, 2Albert-Ludwigs-Universität Freiburg, 3Bavarian Academy of Sciences

Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets Máté Gedeon1, Piroska Barta1, Peter Mihajlik1, Tekla Etelka Graczi2, Anna Kohári3, Katalin Mády4 1Budapest University of Technology and Economics, 2MTA Research Institute for Linguistics & MTA-ELTE "Lendület" Lingual Articulation Research Group, 3Research Institute for Linguistics of the Hungarian Academy of Sciences, 4Research Institute for Linguistics, Hungarian Academy of Sciences

Developing the German Medical Text Corpus (GeMTeX): Legal Compliance and Semantic Enrichment Justin Hofenbitzer1, Christina Lohr2, Andrea Riedel3, Rebekka Kiser1, Aliaksandra Shutsko4, Abanoub Abdelmalak4, Peter Klügl5, Jutta Romberg6, Sarah Riepenhausen7, Miriam Schechner8, Jakob Faller3, Frank Meineke2, Luise Modersohn1, Markus Löffler2, Juliane Fluck9, Udo Hahn10, Stefan Schulz5, Martin Boeker1 1Technical University of Munich, 2Universität Leipzig, 3Friedrich-Alexander-Universität Erlangen-Nürnberg, 4ZB Med, 5Averbis GmbH, 6Charité Berlin, 7University of Münster, 8Ludwigs Maximilian University of Munich, 9ZB MED Information Centre for Life Sciences, 10Friedrich-Schiller-Universitaet Jena

MaiChat: A Text-based Dialogue Corpus Rich in Conversational Features Mai Hoang Dao, Catherine Lai, Peter Bell University of Edinburgh

Saudi ASWAT: A Large-Scale Corpus of Spontaneous Saudi Arabic Speech Abdullah I. Alharbi1, Afrah Altamimi2, Muneera Alhoshan3, Amal Almazrua4, Halah Alharbi5, Bayan Almuqhim5, Hawra Aljasim5, Abdulrahman Alosaimy6, Yahya Asiri7, Abdullah Alfaifi4 1King Salman Global Academy for Arabic, 2KSGAAL, 3King Salman Global Global Academy for Arabic Language, 4KSAA, 5King Salman Global Academy for Arabic Language, 6King Salman Academy for Arabic Language / Imam Mohammed Bin Saud Islamic University, 7King salman global academy of Arabic language

SciCiteVal: A Multi-Domain Dataset for Scientific Citation Verification Qinyue Liu1, Yongxin Zhou2, Cyril Labbe3 1Univ Grenoble Alpes, Laboratoire d'Informatique de Grenoble, 2Université Grenoble Alpes, 3Univ. Grenoble Alpes

RuznamceNER: A Named Entity Recognition Dataset for Ottoman Turkish Esma Bilgin Tasdemir1, Dilara Gürer2, Saziye Ozates2 1Istanbul Medeniyet University, 2Bogazici University

Scripting History: A Diachronic Urdu Text and Image Corpus from the 18Th to 19Th Centuries Sana Shams1, Sahar Rauf2, Asad Mustafa3, Muhammad Javed4, Qurat-ul-Ain Akram5, Sarmad Hussain4, Miriam Butt6 1Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, 2University of Engineering and Technology, 3CLE-UET, 4Center for Language Engineering, KICS, UET, 5UET, 6University of Konstanz

IREKIER: An Easy Read Corpus for Basque and Spanish Jesús Calleja and Thierry Etchegoyhen Vicomtech

15:20 - 17:00

Session P2.1.2: Corpora and Treebanks II - Poster Area

MekongPhon: A Large-Scale Parallel IPA Corpus for Lao and Khmer Ammon Shurtz, Christian Richardson, Stephen Richardson Brigham Young University

CorSpell: Introducing a Semiautomatic Tool for Spelling Normalization in Brazilian Portuguese Juliana Schoffen1, Dennis Giovani Balreira1, Elisa Marchioro Stumpf1, Larissa Goulart2, Tanara Zingano Kuhn3, Rafael Oleques Nunes4, Gabriel Ricci Pazzinato1, Isadora Dahmer Hanauer1, José Henrique de Souza Silva1, Luiza Sarmento Divino1, Marine Matte5 1Federal University of Rio Grande do Sul, 2Montclair State University, 3Research Centre for General and Applied Linguistics (CELGA-ILTEC), University of Coimbra, 4UFRGS, 5Federal Institute Sul-rio-grandense (IFSul)

Meta4XNLI-ptBR: Brazilian Portuguese Extension of Meta4XNLI Corpus Karina Johansson1, Fernanda Assi1, Isabella da Silva2, Rafael Passador1, Isabela Rodrigues1, Aline Paes3, Helena Caseli4 1Federal University of São Carlos (UFSCar), 2Universidade Federal Fluminense (UFF), 3Institute of Computing, Universidade Federal Fluminense, 4Federal University of São Carlos

More than "Oh": Grounding Observable Events with Grunts in Multimodal Dialogue Richard Brutti and James Pustejovsky Brandeis University

COME-ALPs: Coreference Annotation with MErging Heuristics Using ALignment-based Projection in Parallel Corpora gabriela gonzalez saez1, Mariam Nakhle2, Illia Kholosha2, Rachel Atherly2, Marco Dinarelli3 1Universite Grenoble Alpes, 2Université Grenoble Alpes, 3LIG

MEUR: A Benchmark for Evaluating Vision-Language Models on Multimodal Event Understanding and Reasoning Zimu Wang1, Yuqi Wang2, Tong Chen3, Changyu Zeng3, Hongbin Na4, Nijia Han3, Fuyu Xing5, Qi Chen3, Qiufeng Wang6, Anh Nguyen1, Shuihua Wang3, Ling Chen4, Jionglong Su3, Haiyang Zhang3, Wei Wang3 1University of Liverpool, 2Xi'an Jiaotong Liverpool University, 3Xi'an Jiaotong-Liverpool University, 4University of Technology Sydney, 5Carnegie Mellon University, 6Xi'anJiaoTong-Liverpool University

Building Collaborative Speech Corpora for Low-Resource Languages: The Galician Dataset in Mozilla Common Voice Adina Vladu, Elisa Fernández Rei, María Pérez Lago Instituto da Lingua Galega, Universidade de Santiago de Compostela

Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Data Jacob Devasier1, Akshith Putta1, Qing Wang2, Alankrit Moses1, Chengkai Li1 1University of Texas at Arlington, 2The University of Texas at Arlington

A Bilingual Bimodal Benchmark for Arabic-English NLP across Grammatical Correction, Essay Scoring, Morphological Tagging, and Speech Recognition Bashar Alhafni1, Injy Hamed2, Fadhl Eryani3, David Palfreyman4, Nizar Habash5 1MBZUAI, 2Mohamed bin Zayed University of Artificial Intelligence, 3University of Tübingen, 4Zayed University, 5New York University Abu Dhabi

Developing a Guideline for the Labovian-Structural Analysis of Oral Narratives in Japanese Amane Watahiki1, Tomoki Doi1, Akari Kikuchi2, Hiroshi Ohata2, Yuki Nakata3, Takuya Niikawa2, Taiga Shinozaki4, Hitomi Yanaka1 1The University of Tokyo, 2Kobe University, 3Ritsumeikan University, Kobe University, 4Keio University

German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies Jens Rupprecht1, Leon Froehling2, Claudia Wagner2, Markus Strohmaier1 1University of Mannheim, 2GESIS – Leibniz Institute for the Social Sciences

Slovene Morphological and Word Formation Segmentation: A Novel Dataset and Evaluation Marko Pranjic1, Boris Kern2, Ines Voršic3, Senja Pollak4 1Institut "Jožef Stefan", 2ZRC SAZU Fran Ramovš Institute of the Slovenian Language; University of Nova Gorica, 3University of Maribor, 4Jožef Stefan Institute

GePaDeU - a Multi-layer Corpus of German Parliamentary Debates with Rich Semantic and Pragmatic Annotations Ines Rehbein1, Julian Schlenker1, Lars Ostertag2, Simone Paolo Ponzetto1 1University of Mannheim, 2Mannheim University

15:20 - 17:00

Session P2.1.3: Corpora and Treebanks III - Poster Area

What Are LLMs Doing to Scientific Communication? Measuring Changes in Writing Practices and Reading Experience Filip Miletic and Neele Falk University of Stuttgart

GeneFRDebate: Generated French Debates from News Articles with Industrial-Expert Summaries Rim Abrougui, Guillaume Lechien, Elisabeth Savatier, Benoît Laurent Aday

AmbiCoRefVis: A Tool for Visualizing Coreferential Ambiguity Patrick Paetzold1, Lukas Beiske1, Mark-Matthias Zymla1, Massimo Poesio2, Miriam Butt1, Daniel Weiskopf3, Oliver Deussen1 1University of Konstanz, 2Queen Mary University of London and University of Utrecht, 3University of Stuttgart

Fables-DTR: A Corpus of Fables Annotated for Discourse and Temporal Relations Purificação Silvano1, António Leal2, Maciej Ogrodniczuk3, Aleksandra Tomaszewska3, Joana Gomes4, Luís Cunha5, Evelin Amorim6, Martyna Lewandowska3, Anna Sliwicka3, Alípio Jorge7 1University of Porto/ CLUP/ INESC TEC, 2University of Porto/ Centre of Linguistics of the University of Porto, 3Institute of Computer Science, Polish Academy of Sciences, 4University of Porto, 5University of Minho, 6Porto University, 7University of Porto/ INESC TEC

A Benchmark Corpus for the Diagnostic Assessment of Content in L2 English Speech Kosuke Doi1, Justin Vasselli2, Taro Watanabe2 1Seikei University, 2Nara Institute of Science and Technology

Insights from Romanized Manipuri Social Media Text: A Transliteration Corpus and Variation Analysis Maisang Salice, Sanasam Ranbir Singh, Priyankoo Sarmah Indian Institute of Technology Guwahati

MELD: Melding Diverse Multilingual and Multi-Domain Datasets for Named Entity Recognition Evaluation Kevin Glocker and Marco Kuhlmann Linköping University

FinER-ABSA: A Benchmark for Implicit and Explicit Entity Recognition and Aspect-Based Sentiment Analysis in Financial News Pachara Akkanwanich1, Pavorn Thongyoo1, Mahannop Thabua1, Konlakorn Wongpatikaseree1, Natthawut Kertkeidkachorn2 1Mahidol University, 2Japan Advanced Institute of Science and Technology

MUSIA: Multilingual Story Illustration Corpus for Cross-Cultural Alignment and Generation Krishna Tewari1, Supriya Chanda2, Nirmit Patil1, Sukomal Pal1 1Indian Institute of Technology (BHU) Varanasi, 2Bennett University, Greater Noida

MUDiC: A Dataset for Multi-User Dialogue and Collaboration in Chatbot Interaction Nicolas Wagner1, Cristina Luna Jimenez2, Elisabeth Andre3, Wolfgang Minker4, Stefan Ultes1 1University of Bamberg, 2Chair for Human-Centered Artificial Intelligence - Uni Augsburg, 3Universität Augsburg, 4Ulm University

StoryCCDial: Collecting and Analyzing Human-Human Co-Creation Dialogues for Personalized Creative Support Natsumi Ezure and Michimasa Inaba The University of Electro-Communications

DATASHI: A Parallel English–Tashlhiyt Corpus for Orthography Normalization and Low-Resource Language Processing. Nasser-Eddine Monir1 and Zakaria Baou2 1Université de Lorraine, CNRS, Inria, Loria, 2Clermont Auvergne INP - Isima, Université Clermont Auvergne

15:20 - 17:00

Session P2.2: Discourse and Pragmatics I - Poster Area

Evaluating Social Intelligence in LLMs via Japanese Honorifics in Email Generation: A Social Semiotic System Perspective Muxuan Liu1, Tatsuya Ishigaki2, Yusuke Miyao3, Hiroya Takamura4, Ichiro Kobayashi1 1Ochanomizu University, 2National Institute of Advanced Industrial Science and Technology (AIST), 3University of Tokyo, 4The National Institute of Advanced Industrial Science and Technology (AIST)

Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem Tara Azin1, Daniel Dumitrescu2, Diana Inkpen2, Raj Singh1 1Carleton University, 2University of Ottawa

Cross-Lingual and Cross-Cultural Transfer of Talk Move Classification to German Science Classrooms Christian Wartena1, Christian Schumburg2, Andreas Nehring2, Marcel Ebert3, Friederike Korneck3, David Schmitt4, Marie Irmer4, Birgit Neuhaus4 1Hochschule Hannover - University of Applied Sciences and Arts, 2Leibniz Universität Hannover, 3Goethe Universität Frankfurt, 4Ludwig-Maximilians-Universität München

IHPP: A Paragraph-Level Dataset for Investigating the Pragmatics of Hyperpartisan Italian News Michele Maggini1, Davide Bassi2, Angelo Valente3, Gaël Dias4, Pablo Gamallo5 1Centro Singular de Investigación en Tecnoloxías Intelixentes da USC, 2Citius - Universidade de Santiago de Compostela, 3University of Padova, 4Normandie Univ, UNICAEN, ENSICAEN, CNRS, GREYC, 5CITIUS, University of Santiago de Compostela

Detecting Potentially Under-annotated Explicit Discourse Connectives in the Penn Discourse Treebank (PDTB-3) with LLMs Yueh-Ting Chuang1, Xixian Liao2, Bonnie Webber3 1School of Philosophy, Psychology and Language Science, University of Edinburg, 2Barcelona Supercomputing Center, 3University of Edinburgh

Can LLMs Understand Punchlines? LLMs' Narrative Understanding Evaluation with Short-shorts Jiashi Cheng and Takehito Utsuro University of Tsukuba

Building the AURIS Corpus of Reference and Information Structure Christian Chiarcos, Christian Fäth, Tabea Gröger, Quentin Frey University of Augsburg

There Is No Spoon: Existential Presupposition in Large Language Models Marie-Léontine Wörgötter1, Shikai Lai2, Sebastian Schuster1 1University of Vienna, 2University College London

DiscoRAG: A Discourse-Aware Agent for Query-Based Summarization of Long Documents Alexander Chernyavskiy1, Lidiia Ostyakova2, Dmitry Ilvovsky3 1National Research University Higher School of Economics, 2HSE University, DeepPavlov, 3HSE University

15:20 - 17:00

Session P2.3.1: Interpretability, Explainability II - Poster Area

In-Distribution Steering: Balancing Control and Coherence in Language Model Generation Arthur Vogels1, Benjamin Wong1, Yann Choho1, Annabelle Blangero1, Milan Bhan2 1Ekimetrics, 2Sorbonne University, LIP6, LFI

Improving Multilingual Language Models by Aligning Representations through Steering Omar Mahmoud1, Buddhika Semage2, Thommen Karimpanal3, Santu Rana4 1deakin university, 2independent, 3School of Information Technology, Deakin University, 4Applied Artificial Intelligence Institute/Applied Artificial Intelligence Initiative

Explainable AI for Ethical Counter Speech Generation in Hate Speech Mitigation Ashiful Islam Ridoy, Mohammed Faisal, Yogesh Kumar, Md Mamun-Ur Rashid, Marina Ernst, Frank Hopfgartner University of Koblenz

Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis Andor Diera1 and Ansgar Scherp2 1Ulm University, 2University of Ulm

The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective Ali Zahedzadeh and Behnam Bahrak Tehran Institute for Advanced Studies (TeIAS)

Node-Level Uncertainty Estimation in LLM-Generated SQL Hilaf Hasson1 and Ruocheng Guo2 1Cohesity, 2Intuit

A Typologically Grounded Evaluation Framework for Word Order and Morphology Sensitivity in Multilingual Masked LMs Anna Feldman, Libby Barak, JIng Peng Montclair State University

From Generation to Evaluation: A Resource for Error-Categorized Question Generation from Video Transcripts Joshua Berger1, Markos Stamatakis2, Anett Hoppe3, Ralph Ewerth3, Christian Wartena4 1Hochschule Hannover, 2TIB – Leibniz Information Centre for Science and Technology, 3TIB – Leibniz Information Centre for Science and Technology, L3S Research Center – Leibniz University Hannover, University of Marburg and hessian.AI – Hessian Center for Artifical Intelligence, 4Hochschule Hannover - University of Applied Sciences and Arts

From Behavior to Geometry: A Causal and Geometric Analysis of LoRA-Based Domain Adaptation Yizhe WANG, Liu He, Zhenhua Ling University of Science and Technology of China

Explainable Semantic Textual Similarity via Dissimilar Span Detection Diego Miguel Lozano1, Daryna Dementieva1, Alexander Fraser2 1Technical University of Munich, 2Ludwig-Maximilians-Universität München

BIS Reasoning 1.0: The First Large-Scale Japanese Benchmark for Belief-Inconsistent Syllogistic Reasoning Ha Thanh Nguyen1, Hideyuki Tachibana1, Chaoran Liu1, Qianying Liu1, Su Myat Noe2, Koichi Takeda1, Sadao Kurohashi3 1National Institute of Informatics, 2Research and Development Center for Large Language Models,National Institute of Informatics, 3Kyoto University

A Discourse-based Tool Series for Logical Validation of LLMs Boris Galitsky1 and Dmitry Ilvovsky2 1Moscow Institute of Physics and Technology, 2HSE University

15:20 - 17:00

Session P2.3.1: Interpretability, Explainability III - Poster Area

Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation Lina Conti1, Dennis Fucci1, Marco Gaido2, Matteo Negri3, Guillaume Wisniewski4, Luisa Bentivogli3 1Fondazione Bruno Kessler and University of Trento, 2Fondazione Bruno Kessler, University of Trento, 3Fondazione Bruno Kessler, 4Universite Paris Cite and LLF

MUCH: A Multilingual Claim Hallucination Benchmark Jérémie Dentan1, Alexi Canesse2, Davide Buscaldi1, Aymen Shabou3, Sonia Vanier1 1École Polytechnique, 2Ecole polytechnique, 3Crédit Agricole SA

AgriChain: Visually-Grounded Expert-Verified Reasoning for Interpretable Agricultural Vision–Language Models Hazza Mahmood, Yongqiang Yu, Rao Anwer Mohamed bin Zayed University of Artificial Intelligence

SyntaxGym for French: Resource, Annotation, and Evaluation of French and Multilingual LLMs Tatiana Bladier1, Henri-José Deulofeu1, Alexis Nasr2 1Aix-Marseille University, 2Aix Marseille University

Investigating How LLMs Propagate Female Stereotypes: Comparing What Models Say via Prompts with What They Represent in Their Embeddings Andrea Valderrey Nuñez and Jelke Bloem University of Amsterdam

Modeling the Human Lexicon under Temperature Variations: Linguistic Factors, Diversity and Typicality in LLM Word Associations Maria A. Rodriguez1, Marie Candito2, Richard Huyghe1 1University of Fribourg, 2LLF, Université Paris Cité

Object Realisation in Spoken Guadeloupan French: Evaluating NLP Models for an Under-Resourced Variety Amalia Canes Nápoles and Sophie Repp Universität zu Köln

Reason2Decide: Rationale-Driven Multi-Task Learning H M QUAMRAN HASAN1, Housam Khalifa Bashier2, Jiayi Dai1, Mi-Young Kim1, Randy Goebel1 1University of Alberta, 2Alberta Machine Intelligence Institute, Department of Computing Science,University of Alberta

Ragability Benchmark: A Dataset and Library to Test LLMs on Inter-context Conflicts Stephanie Gross, Johann Petrak, Brigitte Krenn Austrian Research Institute for Artificial Intelligence

Evaluating the Adaptability of Large Language Models to Linguistic Variation Ziyan Xu1, Marina Seghier2, Alice Millour3, Carlos-Emiliano Gonzalez-Gallardo4, Jean-Yves Antoine5 1LIFAT Université de Tours, LIASD Université Paris 8, Université de Lorraine, 2Université Paris 8 Vincennes Saint-Denis (LIASD), 3Université Paris 8 Vincennes Saint-Denis, 4LIFAT, Universite de Tours, 5Tours U., LIFAT Lab

Probing Discrete Speech Tokens of Spoken Language Models Sven Naber, Julia Koch, Pranav Singh, Alberto Saponaro, Ioanna Karagianni, Ngoc Thang Vu University of Stuttgart

When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews Hasindri Watawana1, Sergio Burdisso2, Diego Moreno-Galvan3, Fernando Sanchez-Vega4, Adrian Pastor Lopez Monroy5, Petr Motlicek6, Esau Villatoro-Tello6 1Idiap Research Institute, EPFL, 2Idiap, 3CIMAT Centro de Investigacion en Matematicas, 4Center for Mathematical Research (CIMAT), 5Mathematics Research Center CIMAT, 6Idiap Research Institute

17:00 - 17:20

Coffee Break

17:20 - 19:00

Session O9: Corpora, Treebanks and Annotation; Tools, Systems and Platforms - Room 1

17:20 - 17:40

Constructing a Japanese Claim Decomposition Dataset for Fact-Checking of LLM-Generated Texts Miwa Masano1, Ribeka Keyaki2, Atsushi Keyaki1, Rei Minamoto3, Kaito Horio3, Hirokazu Kiyomaru4, Kouta Nakayama4, Hideyuki Tachibana4, Daisuke Kawahara3 1Hitotsubashi University, 2Tokyo University of Technology, 3Waseda University, 4National Institute of Informatics

17:40 - 18:00

Using LLMs for Automatic Discipline Annotation in a Diachronic Corpus of English Scientific Papers Sergei Bagdasarov1, Diego Alves1, Stefan Fischer2, Elke Teich2 1Saarland University, 2Universität des Saarlandes

18:00 - 18:20

COCOA: Creation and Exploratory Investigation of a COrpus of Claims frOm NLP Articles Clémentine Bleuze1, Fanny Ducel2, Maxime Amblard3, Karen Fort4 1LORIA, University of Lorraine, 2LISN, Université Paris-Saclay, 3Université de Lorraine, 4Sorbonne Universite and LORIA

18:20 - 18:40

SPOT: An Annotated French Corpus and Benchmark for Detecting Critical Interventions in Online Conversations Manon Berriche1, Célia Nouri2, Chloé Clavel3, jean-philippe cointet4 1Sciences Po, médialab, 2Inria, Sciences Po, 3INRIA, 4Sciences Po médialab

18:40 - 19:00

MedPT: A Massive Medical Question Answering Dataset for Brazilian-Portuguese Speakers Fernanda Farber1, Iago Brito2, Julia Dollis3, Pedro Schindler Freire Brasil Ribeiro4, Rafael Sousa5, Arlindo Galvão Filho6 1AKCIT, 2Ceia NLP - UFG, 3CEIA - NLP, 4UFG, 5AKCIT / UFMT, 6Federal University of Goiás

17:20 - 19:00

Session O10: Information Extraction and Text Mining II - Room 2

17:20 - 17:40

Large Language Models for Citation Function Classification Daniel Vodicka1, Pavel Kral2, Christophe Cerisara3, Jakub Šmíd4 1University of West Bohemia, 2University of West Bohemia, Dept. of Computer Science and Engineering, 3Universite de Lorraine, CNRS, LORIA, 4University of West Bohemia, Faculty of Applied Sciences

17:40 - 18:00

Small LLMs for Medical NLP: A Systematic Analysis of Few-Shot, Constraint Decoding, Fine-Tuning and Continual Pre-Training in Italian Pietro Ferrazzi1, Mattia Franzin2, Alberto Lavelli2, Bernardo Magnini2 1University of Padova, 2fbk

18:00 - 18:20

Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats Pierre Epron1, Adrien Coulet2, Mehwish Alam3 1INRIA Paris; Telecom Paris, 2Inria, 3Telecom Paris, Institut Polytechnique de Paris

18:20 - 18:40

WISTERIA: Weak Implicit Signal-based Temporal Relation Extraction with Attention Duy Dao DO, Anaïs Halftermeyer, Thi Bich Hanh DAO LIFO - University of Orléans

18:40 - 19:00

Dynamic Model Switching to Mitigate Outdated Knowledge in Large Language Models Ramakrishna Pinninti1, Sabyasachi Kamila2, Ayan Mazumder3, Mohammed Hasanuzzaman4 1Munster Technological University, 2Manipal Institute of Technology, 3IBM, North Carolina, USA, 4ADAPT Centre, Computer Science Department, Munster Technological University

17:20 - 19:00

Session O11: Language Modeling and LRs II - Room 3

17:20 - 17:40

Multi-Scale Model Compression via Nested Matrix Learning Xiangjue Dong1, Aditya Anantharaman2, Hemant Pugaliya2, Kai Zhong2 1Texas A&M University, 2Amazon

17:40 - 18:00

Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection Federica Gamba1, Aman Sinha2, Timothee Mickus3, Raul Vazquez3, Patanjali Bhamidipati4, Claudio Savelli5, Ahana Chattopadhyay2, Laura Zanella6, Yash Kankanampati7, Binesh Remesh2, Aryan Chandramania8, Rohit Agarwal9, Chuyuan Li10, Ioana Buhnila11, Radhika Mamidi12 1Charles University, 2University of Lorraine, 3University of Helsinki, 4International Institute of Information Technology Hyderabad, 5Politecnico di Torino, 6LORIA (Universite de Lorraine, CNRS, Inria), 7Information Sciences Institute, University of Southern California, 8International Institute of Information Technology, Hyderabad, 9UiT The Arcitic University of Norway, 10The University of British Columbia, 11Center for Data Science in Humanities, Chosun University, 12Language Technologies Research Centre, IIIT Hyderabad

18:00 - 18:20

MedInjection-FR: Exploring the Role of Native, Synthetic, and Translated Data in Biomedical Instruction Tuning Ikram Belmadani1, Oumaima El Khettari2, pacome constant dit beaufils3, Benoit Favre4, Richard Dufour5 1Aix-Marseille University, 2Nantes Université - LS2N, 3Nantes university hospital, 4Aix-Marseille University LIS/CNRS, 5LS2N - Nantes University

18:20 - 18:40

The Impact of Tokenization Algorithms on Hungarian Language Model Performance Mátyás Osváth, Máté Norbert Molnár, Roland Gunics, Noémi Ligeti-Nagy ELTE Research Centre for Linguistics

18:40 - 19:00

FAME: Fictional Actors for Multilingual Erasure Claudio Savelli1, Moreno La Quatra2, Alkis Koudounas1, Flavio Giobergia1 1Politecnico di Torino, 2Kore University of Enna

17:20 - 19:00

Session O12: Applications Involving LRs and Evaluation I - Room 4

17:20 - 17:40

Detecting Risky Behavior Related to Alcohol and Drug Use within Adolescents' Private Messenger Conversations Jaromír Plhák1, Michaela Lebedíková2, Ondrej Sotolar1, David Smahel3 1Faculty of Informatics, Masaryk University, 2IRTIS - Interdisciplinary Research Team of Internet and Society, Faculty of Social Science, Masaryk University, 3Masaryk University

17:40 - 18:00

Voices and Echoes in Fictional Dialogue: A Study of Linguistic Coordination in Literary Texts Ioana-Roxana Boriceanu, Alina Iacob, Liviu Dinu University of Bucharest

18:00 - 18:20

Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics Baris Karacan, Barbara Di Eugenio, Patrick Thornton University of Illinois Chicago

18:20 - 18:40

Reading Dynamics and Comprehension in Cognitive Aging: A Multimodal Language Resource Claudia Marzi1, Noemi Boni2, Alice Todesco1, Andrea Nadalini1, Giorgia Albertin3, Cristina Dolciotti4, Paolo Bongioanni4, Marcello Ferro1, Fabio Tamburini3, Gloria Gagliardi3, Vito Pirrelli5 1Institute for Computational Linguistics - CNR, 2University of Pisa, 3University of Bologna, 4Azienda Ospedaliero-Universitaria Pisana, 5Institue for Computational Linguistics - CNR

18:40 - 19:00

Evaluating Style Embeddings for Machine-Generated Text Detection Noé Durandard1, Saurabh Dhawan2, Thierry Poibeau3 1ENS - PSL, 2Technische Universität München, Munich School of Politics & Public Policy, 3LATTICE (CNRS & ENS/PSL)

17:20 - 19:00

Session P3.1.1: Dialogue, Conversational Systems I - Poster Area

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach Nizar El Ghazal, Antoine Caubrière, Valentin Vielzeuf Orange Research

Off the Hamster Wheel: Rethinking Dialogue Research through a Meta-Analysis of the ACL Anthology 2024 Amandine Decker1, Maxime Amblard2, Ellen Breitholtz3 1Universite de Lorraine, 2Université de Lorraine, 3University of Gothenburg

VDAct 2.0: Scaling Video-Grounded Dialogue for Event-driven Activity Understanding with LLM-Assisted Filtering Wiradee Imrattanatrai1, Masaki Asada1, Kimihiro Hasegawa2, Ken Fukuda3, Teruko Mitamura2 1National Institute of Advanced Industrial Science and Technology, 2Carnegie Mellon University, 3AIRC/AIST

Multi-dimensional Evaluation of Character-Authentic Dialogue Models Learned from Question-Answer Data Atsushi Otsuka1, Kazuya Matsuo2, Kenta Hama2, Masahiro Mizukami3, Tsunehiro Arimoto3, Hiroaki Sugiyama4, Makoto Nakatsuji2, Narichika Nomoto2 1NTT Corporation, 2NTT, 3NTT Communication Science Laboratories, 4NTT Communication Science Labs.

Empathy in Greek Exam-Related Support Conversations: A Comparative Evaluation of LLM Responses Panagiota Kyriazi1 and Prokopis Prokopidis2 1Institute of Language and Speech Processing, Athena RC, 2ILSP/Athena RC

Evaluation of Two Leading Polish Language Models in a Real-world RAG Scenario Szymon Bartanowicz and Krzysztof Jassem Adam Mickiewicz University

A Mental State Extraction Dataset for Theory-of-Mind-based Reasoning in Emotional Support Conversations Seulgi Kim and Harksoo Kim Konkuk University

Construction and Analysis of Japanese Parent-Child Dialogic Reading Corpus for Conversational Agents Yuko Nakagi1, Yuya Chiba1, Sanae Fujita2, Shoko Araki1 1NTT Communication Science Laboratories, 2NTT

ACLBot: A Knowledge Graph-Driven Assistant for ACL Anthology Research Jan Buchmann1, Steven Lynden2, Kristiina Jokinen3 1UKP Lab, Technical University of Darmstadt, 2AIST, 3AIRC, AIST and University of Helsinki

This House Debates AI: Evaluating a Language Model in Oxford-Style Debates against Human Experts Umberto Belluzzo1, Kobi Hackenburg2, Hannah Kirk2, Scott Hale3, Paul Röttger2 1Oxford Internet Institute - University of Oxford, 2University of Oxford, 3Oxford Internet Institute, University of Oxford, and Meedan

PAIR: A Pilot Dataset for Dual Perspective-based Video-Grounded Dialogue and Reconciliation Lewis Watson, Carl Strathearn, Kenny Mitchell, Yanchao Yu Edinburgh Napier University

I Am Not Them: Persistent Outgroup Bias in Large Language Models Arising from Social Identity Persona Setting Wenchao Dong1, Assem Zhunis2, Dongyoung Jeong3, Hyojin Chin4, Jiyoung Han3, Meeyoung Cha1 1Max Planck Institute for Security and Privacy, 2Hong Kong University of Science and Technology, 3Korea Advanced Institute of Science and Technology, 4Gyeongsang National University

CONVERSE: Annotation Scheme and Dataset for Multimodal Conversational Engagement Analysis in Human-Human and Human-Robot Interaction Ekaterina Torubarova1, Oskar Ljung2, Julia Uddén3, André Pereira1 1Division of Speech, Music and Hearing, KTH Royal Institute of Technology, 2Department of Linguistics, Stockholm University, 3Department of Psychology, Department of Linguistics, Stockholm University

FineDialFact: A Benchmark for Fine-Grained Dialogue Fact Verification Xiangyan Chen, Yufeng Li, Yujian Gan, Arkaitz Zubiaga, Matthew Purver Queen Mary University of London

17:20 - 19:00

Session P3.1.2: Dialogue, Conversational Systems II - Poster Area

Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models Gaetano Cimino1, Chuyuan Li2, Giuseppe Carenini3, Vincenzo Deufemia1 1University of Salerno, 2The University of British Columbia, 3university of british columbia

HumaniCA: A Benchmark Resource for the Detection of Users' Ascription of Humanness to Conversational Agents Sabrina Villata1, Amon Rapp2, Luigi Di Caro1, Federica Cena1 1University of Turin, 2University of Torino

Towards Reliable Evaluation of Emotional Text Generation in LLMs: Human vs. Automatic Metrics sadegh jafari1, Els Lefever2, Veronique Hoste2 1PhD student at UGent, 2LT3, Ghent University

Question and Response Dynamics in Public Service Encounters Wassiliki Siskou1, Ingrid Espinoza2, Laurin Friedrich3, Steffen Eckhard4, Annette Hautli-Janisz1 1University of Passau, 2Universty of Konstanz, 3University of Konstanz, 4Zeppelin Universität Friedrichshafen

Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems Oier Ijurco1 and Oier Lopez de Lacalle2 1University of the Basque Country UPV/EHU, 2University of the Basque Country

Evaluating the Effect of Question Wording Variations on Answer Consistency in Large Language Models Junya Takayama1, Masaya Ohagi2, Tomoya Mizumoto1, Katsumasa Yoshikawa3 1SB Intuitions, 2SB Intuitions Corp., 3Dai-ichi Life Holdings, Inc.

Knowledge-Infused Hierarchy-Aware Emotion Recognition in Code-mixed Mental Health Counseling Conversations Aseem Srivastava1, Kushagra Mittal2, Anusha Tiwari3, Md. Shad Akhtar4 1MBZUAI, 2IIITD, 3IIIT Delhi, 4Indraprastha Institute of Information Technology, Delhi

A Corpus for Personalized Dialogue Breakdown Repair in Japanese Open-Domain Conversations Kazuya Tsubokura1, Yurie Iribe1, Norihide Kitaoka2 1Aichi Prefectural University, 2Toyohashi University of Technology

Conversational Assistants to Support Patients with Heart Failure: \\ Comparing a Neurosymbolic Architecture with GPT Anuja Tayal, Devika Salunke, Barbara Di Eugenio, Paula Allen-Meares, Eulalia Abril, Olga Garcia-Bedoya, Carolyn Dickens, Andrew Boyd University Of Illinois Chicago

Disentangling Approaches to Conversation Disentanglement: Fine-Tune or Learn from Scratch? Debaditya Pal1, Anton Leuski2, Ron Artstein3, David Traum4, Kallirroi Georgila4 1University of Southern California, 2USC/ICT, 3USC Institute for Creative Technologies, 4University of Southern California Institute for Creative Technologies

Evaluation of Failure Communication Strategies for Trust Repair in Human-AI Collaboration Stina Klein1, Alexandru Wurm1, Elisabeth Andre2, Matthias Kraus3 1University of Augsburg, 2Universität Augsburg, 3Augsburg University

Multi-Session Client-Centered Treatment Outcome Evaluation in Psychotherapy Hongbin Na1, Tao Shen1, Shumao Yu2, Ling Chen1 1University of Technology Sydney, 2KU Leuven

Towards Reward Modeling for AI Tutors in Math Mistake Remediation Kseniia Petukhova and Ekaterina Kochmar MBZUAI

HOTATE: A Japanese Dialogue Corpus Annotated with Responses of Private Thoughts and Public Statements Yuko Toda1, Daisuke Maekawa1, Kota Manabe1, Eito Yoneyama1, Kanade Nonomura1, Yuki Fujiwara1, Tomoyuki Kajiwara2 1Ehime University, 2Ehime University / The University of Osaka

17:20 - 19:00

Session P3.2.1: Less-Resourced/Studied Languages I - Poster Area

Mining Naturally Romanized Seed Corpora without Romanizations Adrian Benton1, Alexander Gutkin1, Christo Kirov1, Brian Roark2 1Google, 2Google Inc.

From Press to Pixels: Evolving Urdu Text Recognition Samee Arif1 and Sualeha Farid2 1University of Michigan, 2University of Michigan - Ann Arbor

HalleluBERT: Let Every Token That Has Meaning Bear Its Weight Raphael Scheible-Schmitt School of Computation, Information and Technology, Technical University of Munich

Sentiment Analysis and Language Models for Kwanyama Ndapa Nakashole University of California, San Diego

TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla Nishat Raihan, Antonios Anastasopoulos, Marcos Zampieri George Mason University

ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models Duy Nguyen1, Chinh Truong2, Tr?n Phúc3, Hung Le4, Nguyen Dat5, Trung Hieu Pham3, Kiet Nguyen6 1Industrial University of HoChiMinh City; Military Hospital 175, 2Military Hospital 175, 3Pythera AI, 4University of Information Technology, HCM VNU, 5University of Information Technology, 6University of Information Technology, VNU-HCM

Creating Task-Specific Speech Recognition Datasets from Scratch for Low-Resource Languages: Assessing the Impact of Token Sequence Overlap Adwoa Bremang, Dennis Asamoah Owusu, Victor Quagraine, Leanne Annor-Adjaye Ashesi University

Radio Haiti-Inter: A Large-Scale Annotated Corpus of Spoken Haitian Creole William Havard1, Rayan Ziane2, Mélissa Menclé3, Maximin Coavoux4, Benjamin Lecouteux5, Emmanuel Schang3 1Laboratoire Ligérien de Linguistique, Université d'Orléans, 2Laboratoire Ligérien de Linguistique, 3Université d'Orléans, 4CNRS, Univ Grenoble Alpes, 5LIG/GETALP

Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages Nick McKenna1, Xinnuo Xu2, Jack Williams2, Nicholas Wilson3, Benjamin Van Durme4, Christian Poelitz2 1GitHub Applied Science, 2Microsoft Research, 3Microsoft, 4Johns Hopkins University / Microsoft

PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models Mohammad Hosseini1, Kimia Hosseini1, Shayan Bali2, Zahra Zanjani1, Saeedeh Momtazi1 1Amirkabir University of Technology, 2King's College London

ADAB: Arabic Dataset for Automated Politeness Benchmarking - a Large-Scale Resource for Computational Sociopragmatics Hend Al-Khalifa1, Nadia Ghezaiel2, Maria Bounnit3, Hend Alhazmi4, Noof Alfear1, Reem Alqifari1, Ameera Almasoud5, Sharefah Al-Ghamdi1 1King Saud University, 2College of computer Science and software Engineering, 3Cadi Ayyad University, 4Saudi Center Of Philosophy and Ethics, 5KSU

GRDD+: An Extended Greek Dialectal Dataset with Cross-Architecture Fine-tuning Evaluation Stergios Chatzikyriakidis1, Dimitri?s Papadakis1, Sevasti Papaioannou2, Erofili Psaltaki3 1University of Crete, 2National and Kapodistrian University of Athens, 3University of Turku

Same-Language Subtitles for Low-resource Languages: A Case of Bundelkhandi Anirudh Pradhan1, Ayushi Pandey1, Divyansh Kushwaha1, Akshita Tiwary1, Vivek Seshadri2 1Karya, 2Microsoft Research India / Karya Inc

Chulalongkorn Corpus of Spoken Thai Pittayawat Pittayaporn1, Cathryn Yang2, Sujinat Jitwiriyanont1, James Kirby3 1Center of Excellence in Southeast Asian Linguistics, Chulalongkorn University, 2Payap University and SIL Global, 3Ludwig Maximilian University of Munich

Nepal Script Text Recognition from Ancient Artifacts: Challenges and Opportunities Swornim Nakarmi1, Sarin Sthapit1, Sahil Tuladhar1, Arya Shakya1, Bal Krishna Bal2, Rajani Chulyadyo2 1Kathmandu University, 2Department of Computer Science and Engineering, Kathmandu University, Nepal

LuxBorrow: From Pompier to Pompjee, Tracing Borrowing in Luxembourgish Nina Hosseini-Kivanani1 and Fred Philippy2 1RTL & University of Luxembourg, 2University of Luxembourg

Ramsa: A Large Sociolinguistically Rich Emirati Arabic Speech Corpus for ASR and TTS Rania Al-Sabbagh University of Sharjah

17:20 - 19:00

Session P3.2.2: Less-Resourced/Studied Languages II - Poster Area

ForumOccitania: A Corpus of User-Generated Content for Multiple Occitan Varieties Oriane Nédey1, juliette janes1, Rachel Bawden1, Thibault Clérice2, Benoît Sagot1 1Inria, 2ALMAnaCH, Inria

A Dataset of Wolof Ajami Manuscripts for HTR and OCR Oreen Yousuf1, Elhadji Djibril Diagne2, Christian Høgel3, Beata Megyesi4, Joakim Nivre1 1Uppsala University, 2Murid Islamic Community in America, Inc. (MICA, Inc.), 3Lund University, 4Department of Linguistics, Stockholm University

TDMulti: A Tunisian Dialect-Modern Standard Arabic Multitask Corpus with a Context-Aware Cross-Attention BERT Model Roua Torjmen1 and Kais HADDAR2 1Faculty of Sciences of Sfax, 2University of Sfax

The Megrelian Language Corpus (MLC): Creation, Annotation, and Initial Steps toward a UD Treebank Irina Lobzhanidze1, Rusudan Gersamia1, Tamar Gogia2 1Ilia State University, 2Pompeu Fabra University

Steering LLMs toward Korean Local Speech: Iterative Refinement Framework for Faithful Dialect Translation keunhyeung park, Seunguk Yu, Youngbin Kim Chung-Ang University

LombardoGraphia: Automatic Classification of Lombard Orthography Variants Edoardo Signoroni and Pavel Rychly NLP Centre, Faculty of Informatics, Masaryk University

Meenz bleibt Meenz, but Large Language Models Do Not Speak the Dialect of Mainz Minh Duc Bui1, Manuel Mager2, Peter Kann3, Katharina von der Wense4 1University of Mainz, 2Amazon AWS, 3Philipp's University Marburg, 4University of Colorado Boulder

Bootstrapping NLP for Sakha: Named Entity Recognition and Sentiment Analysis in an Extremely Low-Resource Setting Mariia Everstova, Nikolai Efimov, Valerio Basile University of Turin

Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages Ubaid Azam1, Imran Razzak2, Shoaib Jameel1 1University of Southampton, 2UNSW

A Parallel Corpus of the Parable of the Prodigal Son: Building a Resource for Documenting Language Varieties in Metropolitan France Lucence Ing1, juliette janes1, Sven Ködel2, Benoît Sagot1 1Inria, 2Institut historique allemand

Developing Zila: A Spoken Language Resource for the Endangered Slovenian Gail Valley Dialect Andrej Zgank1, Gregor Donaj1, Urh Kolaric1, Usi Sereinig2, Tatjana Koren-Zwitter3, Sanja Boto3, Sabina Zwitter-Grilc4, Jasna Vidinic1, Darinka Verdonik1 1University of Maribor, 2Slovenian Ethnographic Institute Urban Jarnik, 3Mohorjeva Hermagoras, 4ORF Kärnten

Nawatl Context-Free Grammars for Natural Language Processing Juan Jose Guzman Landa1, Juan-Manuel Torres-Moreno2, Graham Ranger3, Miguel Figueroa-Saavedra4, Ligia Quintana Torres4, Carlos-Emiliano Gonzalez-Gallardo5, Luis Moreno Jimenez6, Martha Lorena Avendaño Garrido4 1Universite Avignon, 2LIA Avignon, 3Univeristé d'Avignon, 4Universidad Veracruzana, 5LIFAT, Universite de Tours, 6Sorbonne Université

Physical Commonsense Reasoning for Lower-Resourced Languages and Dialects: A Study on Basque Jaione Bengoetxea1, Itziar Gonzalez-Dios2, Rodrigo Agerri3 1HiTZ Center - Ixa, University of the Basque Country UPV/EHU, 2HiTZ Basque Center for Language Technologies - Ixa, University of the Basque Country UPV/EHU, 3HiTZ Center - Ixa, University of the Basque Country EHU

Common Voice for Pakistan: Developing an Open Speech Corpus for Low-Resource Pakistani Languages Meesum Alam1 and Francis Tyers2 1Indiana University Bloominton, 2Indiana University

Amulwe Kimün: A Community-Grounded Demo, Resource, and ASR Baseline for Mapuzugun Cristian Ahumada Oliva1 and Fatiha Sadat2 1Université du Québec À Montreal, 2UQAM

Development of Serbian QA Datasets through Prompt-Based Generation and Human Validation Jovana Radenovic1, Olivera Kitanovic2, Ranka Stankovic3, Mihailo Škoric4 1Faculty of Mining and Geology, University of Belgrade, 2researcher, 3University of Belgrade - Faculty of Mining and Geology, 4University of Belgrade Faculty of Mining and Geology

An Enhanced Pipeline for the Manzini-Savoia Corpus Achille Fusco1, Greta Mazzaggio2, Carlo Zoli3 1University of Florence, 2Université de Neuchâtel, 3Free University of Bozen-Bolzano

17:20 - 19:00

Session P3.2.3: Less-Resourced/Studied Languages III - Poster Area

Are Language Models Borrowing-Blind? A Multilingual Evaluation of Loanword Identification across 10 Languages Merilin Sousa Silva and Sina Ahmadi University of Zurich

Comparing Approaches to Automatic Summarization in Less-Resourced Languages Chester Palen-Michel1 and Constantine Lignos2 1Ebay, 2Brandeis University

PsihoRo: Depression and Anxiety Romanian Text Corpus Alexandra Ciobotaru1, Ana-Maria Bucur2, Liviu Dinu1 1University of Bucharest, 2Università della Svizzera italiana

Aligned Parallel Corpus of the Vedic Sa?hitas for Machine Translation Yuzuki Tsukagoshi and Ikki Ohmukai The University of Tokyo

FormosanMT: A Multilingual Parallel Corpus of the Formosan Language Family Hunter Scheppat1, Joshua K. Hartshorne2, Sema Koc1, Éric Le Ferrand1, Emily Prud'hommeaux1 1Boston College, 2MGH Institute of Health Profession

The Construction of a Mixe Variant Parallel Corpus Ivan Vladimir Meza Ruiz1, Delfino Zacarias Marquez2, Martha Elba Ramírez Andrés3, Victoriano Santiago Cayetano3, Jonathan Santiago Antonio3, Carlos Daniel Hernández Mena4 1Insituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México, 2INEGI, 3UNTI México, 4BSC

Nepali Lemmatization with Multilingual Transformers: Intrinsic and Extrinsic Evaluation in a Low-Resource Setting Sunil Regmi1, Sundeep Dawadi1, Bal Krishna Bal2 1Kathmandu University, 2Department of Computer Science and Engineering, Kathmandu University, Nepal

Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands Maori Rolando Coto-Solano1, Daisy Li1, Manoela Teleginski Ferraz1, Olivia Sasse1, Cha Krupka1, Sharid Loáiciga2, Sally Akevai Nicholas3 1Dartmouth College, 2University of Gothenburg, 3University of Auckland

A Modern Online Learning Platform for ?Olelo Hawai?i Classrooms Christian Castro1, Keneth Martin2, Winston Wu3, William Wilson2 1University of Hawai'i Hilo, 2University of Hawaii at Hilo, 3University of Hawaii

Glossed Data in Northern Interior Salish Anna Stacey University of British Columbia

CEFR-Cymraeg: A Dataset and Baseline Models for Language Proficiency Assessment in Welsh Eeshan Waqar, Jonathan Davies, Dawn Knight, Fernando Alva-Manchego Cardiff University

Singlish to English Translation with Precision: A Dataset and Language Detection-Driven Masked Modeling for Singlish to English Translation Sujit Kumar1, Gerome Ang2, Stephanie Hilary Xinyi Ma3, Andy Hau Yan Ho3, Andy Khong3 1Postdoctoral Research Fellow, Nanyang Technological University Singapore, 2Lee Kong Chian School of Medicine, Nanyang Technological University, 3Nanyang Technological University

LLMs in Ottoman Turkish: From MLM to NER Enes Yilandiloglu University of Helsinki

SloPal: A 60-Million-Word Slovak Parliamentary Corpus with Aligned Speech and Fine-Tuned ASR Models Erik Božík1 and Marek Suppa2 1VUB, 2Comenius University in Bratislava

SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction Dávid Števanák1 and Marek Suppa2 1University of Vienna, 2Comenius University in Bratislava

Automatic Speech Recognition for Documenting Endangered Languages: Case Study of Ikema Miyakoan Chihiro Taguchi1, Yukinori Takubo2, David Chiang1 1University of Notre Dame, 2NINJAL

Adaptive Method for Self-Supervised Learning Models on Automatic Dialect Speech Recognition Based on Shared Knowledge of Japanese Dialects and Standard Japanese Naoru Asakawa1, Naoki Takahashi1, Atsuhiko Kai1, Seiichi Nakagawa2 1Kai Lab, Shizuoka University, 2Shizuoka University

19:00 - 20:00

ELRA General Meeting - Room 1

20:00

LREC 2026 Welcome Reception

End of Day 1