Long papers

• A Constraint-Based Formalism for Controlled Text Generation
  Lionel Clément
• Can we use LLMs to generate data-driven patient narratives? A multi-method exploration in the oncology domain
  Nele Albers, Linwei He, Anouk Teunissen, Kelly M. de Ligt, Nadine Bol, Emiel Krahmer
• Chain-of-Thought Depth Modulates Performance by Task and Model: Evidence from Ablation Studies Across Five Model Families
  N.ANEESH.DUTT
• ADR-Control: Do LLM Coding Agents Follow Architectural Decisions? An Evaluation of ADR-Grounded Code Generation
  Pham The Phong, Phan Duy Hung
• Not All Linguistic Capabilities Degrade Equally Under Quantization
  Arunabh Majumdar
• Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions
  Aditya Agrawal, Alwarappan Nakkiran, Alex Karlsson, Aman Singh Thakur, Harsha Aduri
• ViInfoSum: A Novel Dataset for Multimodal Summarization in Vietnamese
  Nguyen Khoi Tran, Binh Xuan Le, Nghia Hieu Nguyen, Khiem Vinh Tran, Ngan Luu-Thuy Nguyen
• From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification
  Mai Mohamed Eida, Gunjan Anand, Ayush Singh, Aleksandre Maskharashvili
• Metric Cards Make Blind Spots Legible
  Minh Anh Nguyen, Nils Feldhus
• Augmenting Lecture Information via Redundancy-Filtered LLM Slide Descriptions for Blind and Low-Vision Students
  Katharina Anderer, Jan Niehues, Karin Müller, Matthias Wölfel
• PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference
  Weisheng Jin, Maojia Song, Tej Deep Pala, Yew Ken Chia, Dorien Herremans, Soujanya Poria
• FJ-Guard: Persistence-Guided Training-Free Defense for LLM-based Multi-Agent Systems
  Yudai Yamazaki, Kentaro Kita, Hiroya Kato, Kento Hasegawa, Seira Hidano
• CAAF: Confidence and Agreement-Aware Fusion for Multi-LLM Ensembles
  Momojit Biswas, Preethu Rose Anish
• Towards Green Text Generation: Memory-Based Speculative Decoding
  Antal van den Bosch
• Decomposed Entailment for Factuality Checking and Hallucination Detection
  Achir Oukelmoun, Nasredine Semmar, Gaël de Chalendar
• What Did My Adapter Break? A Generation-Level Evaluation of Adaptation and Retention in PEFT-Adapted LLMs
  Guy Bilitski, Kfir Bar, Shai Fine
• Translating Classical Poetry into Modern Prose
  Chalamalasetti Kranti, Sowmya Vajjala
• Self-Verification is All You Need To Pass The Japanese Bar Examination
  Andrew Shin
• Automatic vs. Human Evaluation: Benchmarking 26 Automatic Metrics for Clinical Discharge Summaries
  Yu-Wen Chen, Anne de Hond, Laura Veerhoek, Ruben Peters, Karel GM Moons, Artuur Leeuwenberg
• Hierarchical Experience Memory for Multi-Agent Task Planning and Subtask Guidance
  Marcus Lee
• Dynamic Intent-Driven API Pruning for Tool Learning in Small Language Models
  Tzu-Hao Wang, Ting-Chun Yang, Sin-Syuan Wu, Yao-Chung Fan
• Confident by Default: A Longitudinal Study of Style Drift and Convergence Across Large Language Model Providers
  Silas Rech, Tom Bäckström
• Generating Critical Questions for Arguments: A Large-Scale Analysis of Prompting and Reranking Strategies
  Midhun Kanadan, Benno Stein
• From Sounds to Symbols: A Survey of Phonetically and Phonologically Informed Language Generation
  Tyler Loakman, Joseph James, Chenghua Lin
• Do as I Say, Not as You Do: Assessing Public Versus Practitioner Perspectives on the Development of Artificial Intelligence and Language Technologies
  Tyler Loakman, Chenghua Lin
• Structured Critique Generation Mitigates Toxification in Self-Critique Alignment
  Takeru Mitsumori, Hiroya Takamura, Takashi Inui
• EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages
  Aleix Sant, Jordi Luque, Carlos Escolano
• Mid-Utterance Transition Control for Audio Commentary Generation
  Ryota Kawamatsu, Tatsuya Ishigaki, Hiroya Takamura
• Effort and Confidence: Surface Markers in Reasoning Traces Predict Correctness on Insight Puzzles
  Richard A. J. Mann, Pranava Madhyastha
• Chain-of-Thought Faithfulness Under GRPO and DPO Fine-Tuning
  Hadi Mohammadi, Anastasia Giachanou
• Trust Stack for Mental Health AI: A Survey of Calibration across Human, Interaction, and AI Layers
  Xin Sun, Yue Su, Yifan Mo, Qingyu Meng, Yuxuan Li, Min Chen, Mengyuan Zhang, Saku Sugawara, Charlotte Gerritsen, Sander L. Koole, Koen Hindriks, Jiahuan Pei
• Large Language Models for Data Augmentation in Product Matching
  Kateřina Macková, Martin Pilát
• Persona as a Dynamical System: Attractor-Based Character Control for Neural Text Generation
  Yu-Yi Chang, HAOCHE CHIU, Hung-Yu Kao
• Content Determination Is the Faithfulness Bottleneck: A Computable-Oracle Benchmark for Faithful LLM Explanations of Guardrail Decisions
  Arunkumar V
• Decoding Path Recovery in Number Generation: Shifting to Intermediate Layers and Top-$k$ Ranks
  Jasivan Alex Sivakumar, Nafise Sadat Moosavi
• Cross-Lingual Activation Steering for Multilingual Language Models
  Rhitabrat Pokharel, Ameeta Agrawal, Tanay Nagar
• Beyond Natural Language Plans: Structure-Aware Agentic Planning for Query-Focused Table Summarization
  Weijia Zhang, Yifei Yuan, Songgaojun Deng, Evangelos Kanoulas
• Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
  Joris Baan, Wilker Aziz, Barbara Plank, Raquel Fernández
• A Large-Scale Dataset for Cross-Lingual Multi-Jurisdiction Patent Drafting from Patent Cooperation Treaty Applications
  Trung Phuong Le, Hirofumi Nonaka, Koji Marusaki, Katsuhito Sudoh, Seiya Kawano
• Identifying Check-Worthy Claims by Generating the Implicit Content of Enthymemes
  Martial Pastor, Stefan Kok
• Beyond Agreement: Compositional Validity in Multidimensional LLM Evaluation
  Savita Bhat, Vasudeva Varma
• Perspective-Diverse Utterance Candidate Generation via Input Variation for Race Game Commentary
  Mizuki Arai, Tatsuya Ishigaki, Yusuke Miyao, Hiroya Takamura, Ichiro Kobayashi
• Revealing Current Performance of LLMs in Multi-Agent and Long Logical Context by Automatically Playing the Werewolf Game As a Contest
  Yoshinobu Kano, Yuya Harada, Yuto Sahashi, Daisuke Katagami, Kei Harada, Michimasa Inaba, Takeshi Ito, Hirotaka Osawa, Takashi OTSUKI, FUJIO TORIUMI
• Pop Quiz! Comparing Educational Assessment Methods for Evaluating Context Utilization vs. Pre-Trained Knowledge in Large Language Models
  Anura Deshpande, Suvaditya Mukherjee, Benjamin Nye, Ella Park, Russell Harral
• TENOR: Tension-Enhanced Narrative Planning and Organization for Report Generation
  Aliah Gie Fajardo Zabala, Yi-Shin Chen
• NexusEngine: Ontology-Constrained, Provenance-Grounded, Multi-Modal Generation for Infrastructure Digital Twins
  Kanimozhi Uma, Merijn Vanalderweireldt
• Probing the Communicative Efficiency of LLMs via Content Selection in Visually Uncommon Reference Games
  Simeon Junker, Manar Ali, Kristina Kobrock, Larissa Koch, Marika Sarzotti, Hendrik Buschmeier, Sina Zarrieß
• Are LLM Judges Language-Neutral? A Cross-Lingual Meta-Evaluation on Multilingual Summarization
  Mohammaderfan Koupaei, Amir Esmaeili, Mahshid Khanali, Florian Mai, Patrícia Schmidtová
• One Feedback System Does Not Fit All:Localising Data-to-Text Driver Coaching for the UK and Nigeria
  Iniakpokeikiye Peter Thompson, Jawwad Baig, Ehud Reiter, Dewei Yi
• Controllable Lexical Alignment in Dialogue Systems
  Sumit Srivastava, Mariët Theune, Alejandro Catala
• More Than Rainfall: A Multi-Dimensional Analysis of LLM Flood Cause Multi-document Summarization for Disaster Risk Management
  Jane Arleth dela Cruz, Jarno Van Arkel, Iris Hendrickx, Martha Larson
• When More Extractive Summaries Receive Higher Automated Factuality Scores: Evidence from Distilled Scientific Summarization
  Joseph Moretto, Peter A. Beling, Tyler Cody
• A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty Quantifiers
  Evgenia Ilia, Wilker Aziz
• Language-Agnostic Latent Injection for Multilingual Hybrid Reasoning
  Đặng Phương Nam, Nguyen Van Hieu, Nguyen Nam Truong, Phan Duy Hung
• Refusal in the Tail: Surfacing Latent Abstention for Context-Refuted Queries
  Hansle Lee, Jaeeun Jang, sangmin kim
• Graph Mapping and LLMs Thinking Speed
  Ramazan Ali Bahrami, Ramin Yahyapour
• Towards Plug-and-Play Attribute Control Modules in Text Generation: An Exploratory Study of LoRA Portability Across Model Families
  Michela Lorandi, Anya Belz
• Probing, Measuring and Mitigating Activity-Level Gender Associations in Open-Ended Text Generation
  Xiangjue Dong, Yibo Wang, Philip S. Yu, James Caverlee
• Exploring the feasibility of ontology-based educational question generation with an LLM
  Franco Alberto Cardillo, C. Maria Keet, Zola Mahlaza
• AdTEx: Evaluating Large Language Models for Diverse Advertisement Template Expansion
  Hiroto Otake, Peinan Zhang, Yusuke Sakai, Hiroki Ouchi, Taro Watanabe
• InduceGuard : Evaluating Induction Resistance of Large Language Models under Multi-turn Prohibited Keyword Elicitation
  Shunichi Yoneda, Yukitake Yoshioka, Yurai Takayanagi, Yumi Fukuda, Ryoma Obara, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Shogo Matsuno
• ACA-Bot: Evaluating Pedagogical Dialogue Generation in a Spoken LLM-Based Oral Examiner
  Julie Bauer, Krist Shingjergji, Aki Härmä
• The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
  Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann, Matthias Aßenmacher
• A Writer–Editor–Critic Pipeline with Deterministic Fact Verification for Football Match Report Generation
  Luís Relvas, Sérgio Nunes, André Restivo
• Token Distribution versus Data Volume: Domain Balancing in Multi-Domain Meeting Summarisation
  Ashima Sood, Bryan Gardiner, Joan Condell
• Frugal Source-Grounded Detection of Graded Omissions in LLM-Generated French Medical Summaries
  Benouaklil Hodhaifa, Nasredine Semmar, Achir Oukelmoun, Faiza BELBACHIR, Jaafer klila, Hassane Essafi
• Comparing Retrieval-Augmented Generation Pipelines for Energy-Aware Code Refactoring
  Youssef Oubelmouh, Pierre CHHIENG, Daoudi Amir Salah Eddine
• Confabulation in a Caption-then-Generate Pipeline: Evaluating Vision–Language Generation of Adolescent Health Information
  Abigail Naa Amankwaa Abeo, Steven Smith, Hannah Goss, Michael Scriney
• A Multi-Faceted Analytical Framework for Text Quality Evaluation in Creative Open-Ended Generation
  Esteban Garces Arias
• Rate-Resolved Text Evaluation with Masked Diffusion Language Models
  Yiqi Liu, Kun Zhao, Chenghua Lin, Nafise Sadat Moosavi
• Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement
  Yiqi Liu, Flavjo Tomori, Nafise Sadat Moosavi, Steffen Eger, Chenghua Lin
• JudgeMoE: Distributional Aggregation for LLM-as-a-Judge
  Yiqi Liu, Joseph James, Yang Wang, Kun Zhao, Chenghao Xiao, Chenghua Lin
• Retell, Reward, Repeat: Reinforcement Learning for Narrative Theory-Informed LLM Story Retelling
  David Y. Liu, Xanthe Muston, Dipankar Srirag, Aditya Joshi, Paul Dawson, Sebastian Sequoiah-Grayson
• Do We Really Need So Many Tokens? The Performance-Efficiency Trade-off in Tibetan and Sanskrit
  Orr Meir Zwebner, Kai Golan Hashiloni, Guy Bilitski, Oded Hellman, Nir Marciano, Shai Fine, Kfir Bar
• A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement
  Carmel Kronfeld, Sharva Gogawale, Tetsuro Kobayashi, Irad Ben Gal
• CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  Farhana Amin, Sabiha Afroz, Dimitrios S. Nikolopoulos
• M$^{2}$Preserve: A Multidimensional Framework for Evaluating Meaning Preservation in Text Simplification
  Abdullah Barayan, Jose Camacho-Collados, Fernando Alva-Manchego
• In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
  Anudeex Shetty, Aditya Joshi, Salil S. Kanhere
• Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation
  Elaf Alhazmi, Quan Z. Sheng, Wei Emma Zhang
• Automating Multi-Hop RAG Evaluation via TRIAD: From Context Extraction to Validated Dataset Generation
  Lorenz Brehme, Adam Jatowt
• Can LLM Coding Agents Reason About Time Series?
  Filip Rechtorík, Ondrej Dusek, Zdeněk Kasner
• Strategies for Span Labeling with Large Language Models
  Danil Semin, Ondrej Dusek, Zdeněk Kasner

Short papers

• You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs
  Hyunwoo Kim, Usama Khalid
• Example-Guided Prompting for Document-Level Text Simplification
  Marina Litvak, Ariel Perstin, Ilan Shtilman, Michael Färber
• Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With?
  Alberto Cetoli
• The Impact of Model Size on Detection of LLM Hallucinations
  Matt Boerio, Paul Groth
• Assessing Legal Argumentation in Generated Judgments: A Toulmin-Based Evaluation Framework
  Cor Steging, Tadeusz Zbiegień
• Heterographic Supervision for Direct Speech-to-Text Translation in Scriptless Tribal Languages
  Prashant Bannulmath, Swapnil Sontakke, Deepak K T
• From Full Game State to Live Commentary: A Data-to-Text Pipeline and Corpus for Age of Empires II
  Siewart van Wingerden
• From Metrics to Meaning: Learning Qualitative Research Methods as a Community
  Adarsa Sivaprasad, Yujun Wang, Mengxuan Sun, David M Howcroft, Ehud Reiter
• Distractors for Multiple-choice Questions for Reading Comprehension: Automatic Generation and Evaluation
  Yixi Chen, Shunjie Wang, LI JIAYI, John Sie Yuen Lee
• Do LLMs Make More Mistakes If They Do Not Believe the Input Data?
  Peter Kochelka, Aleš Manuel Papáček, Vojtěch Dvořák, Ondrej Dusek
• A Cognitively Motivated Multidimensional Framework for Evaluating Metaphor Explanations
  Ana Naveriani, Jakob Suchan, Stefano Zoia, Mehul Bhatt, Antonio Lieto, Gian Luca Pozzato
• When Diverse Paraphrases Do Not Help: LLM Data Augmentation for Portuguese Aspect-Based Sentiment Analysis
  Andrew Borges de Campos, Gabriel A. Gomes, Larissa Astrogildo de freitas, Ulisses Brisolara Corrêa
• Evaluating Rationale-Grounded Responses for Meme Images via Self-Scoring-Based Selection
  Ryotaro Kanae, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

Demo papers

• CAP: Contrastive Activation Patching for Locating, Comparing, and Steering Neurons in Multilingual LLMs
  Aleksandr Semenikhin
• PLeW-NLG: Interactive Exploration of Human Evaluation Data across NLG Tasks
  Fahime Same, Leonard W Sprague Jr, Francesco Cangemi
• A Tool for Collecting Validated Triple Sets for Data-to-Text Generation
  Mark Andrade, Simon Mille, Anya Belz, Brian Davis
• TruthSplit: Interactive Generation of Multi-Perspective Reasoning Graphs for Contested Claims
  Lion Six, Adrien Zaradez, Thomas Huber, Christina Niklaus
• SeanchlÓCR: A platform for Transformer-based transcription of Irish Gaelic Script
  Sháhín de Faoite Houshidari, Brady Meade, Ellen Rushe

Non-Archival submissions

Note: Presented during the INLG poster sessions and not included in the proceedings.

• BikeCoach: A Demo System for Aspect-based Advice Generation Conditioned on Sport Training Protocols
  Matīss Rikters, Tatsuya Ishigaki, Masayuki Kawarada, Shota Kato, Sohei Washino, HirokiYamaguchi
• Knowledge-Grounded Generation and Agentic Verification for Describing Swine Health Status from Farm Images
  Eunji Lee, Minseok Kim, Parkhyungwook
• Knowledge Graph Prompting for Multi-hop Reasoning
  Al Hasib Mahamud, Yllias Chali
• ANVIL: Analogies and Videos for Lecturers
  Yuri Noviello, Anastasiia Birillo, Gosia Migut
• A Comparative Evaluation of End-to-End and Pipeline Approaches for Summarisation
  Fahime Same, Saad Mahamood, Srinivas Ramesh Kamath
• Criterion Definitions, Not Criterion Names, Determine What an LLM Judge Measures
  Srinivas Harish
• VISTA: Verification In Sequential Turn-based Assessment
  Ashley Lewis
• Dual use issues in the field of Natural Language Generation
  Emiel van Miltenburg
• Justify your prompts!
  Eduardo Calò, David M Howcroft, Leo Leppänen, Saad Mahamood, Simon Mille, Patrícia Schmidtová, Emiel van Miltenburg
• Never Truly Out of Fashion: A Retrospective Look at Evaluation in NLG
  Patrícia Schmidtová, Saad Mahamood, Ondrej Dusek
• AI-Assisted Length-Constrained Summarization in News Agency Workflows
  Aleksandra Gabryszak, Damian Jaspar, Shushen Manakhimova, Leonhard Hennig
• Reasoning Gets Harder for LLMs Inside A Dialogue
  Ivan Kartáč, Mateusz Lango, Ondrej Dusek
• VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations
  Ivan Kartáč, Jan Tovarys, Mateusz Lango, Ondrej Dusek
• DeScribe: Discourse-Driven Extraction and Structuring of Claim Verification for Better Faithfulness Evaluation
  Yang Zhong, Yang Janet Liu, Diane Litman
• Testing Associative Creativity in Humans and Multimodal LLMs with Difficult-to-Name Visual Stimuli
  Manar Ali, Lisa Gottschalk, Simeon Junker, Lisa Hudalla, Alon Fishman, Joana Cholin, Stefan Kopp, Hendrik Buschmeier, Sina Zarrieß
• When Seekers Are Hard to Help: Evaluating Emotional Support Dialogue Systems in Worst-Case Interactions
  Jiajie Yang, Yangchun Li, Guanyi Chen, Rui Fan, Xin Bai, Tingting He
• Beyond Single Gold Labels: Human Variability and Conceptualisation in Chinese Classifier Use
  Yongheng Peng, Guanyi Chen, Tingting He
• Ontology-Mediated Framework for Generating Answerable Questions and Feedback from Ontologies
  Toky Hajatiana Raboanary, C. Maria Keet
• When Wrong Answers Sound Coherent: Evaluating Answer-Conditioned Explanatory Generation in LLMs
  Göktuğ Aslanoğlu, Viswanadh Vadlamani
• Preliminary results on predicting bootstrapping NLG resources for low-resourced languages
  Phuthang Makhupane, Leruo Hillary Sharp, Zola Mahlaza, C. Maria Keet
• Compliance Assessment and Justification Generation for Journalistic Self-Regulation
  Aleksandra Gabryszak, Danylo Mysak, Shushen Manakhimova, Leonhard Hennig
• Same Text, More Tokens: Layerwise Attention Distortion under Retokenization
  Baban Gain, Asif Ekbal
• Modular Multilingual Language Models with Language-Specific Embeddings
  Nalin Kumar, Ondrej Dusek
• Expert Disagreement as Signal: Evaluating Clinical NLG Without Reference Reports
  Yongxin Zhou, Fabien Ringeval, François Portet
• DBpedia Triple Set Validation for Consistent NLG Inputs
  Mark Andrade, Simon Mille, Anya Belz, Brian Davis
• Stress Testing NLG Evaluation Metrics with Fine-Grained Semantic Contrasts
  Lasha Abzianidze
• Calculation Is Not Insight: Qualitative Reasoning for Data-to-Text Generation
  Kristýna Onderková