Oral Presentation
The AACL-IJCNLP 2026 main conference features 148 oral papers across 25 sessions (November 6 – 8, 2026). Click a session in the table of contents to jump to its papers.
Session 1.1: Resources and Evaluation 1
Friday, November 6, 11:00-12:30 · Muhe B+C
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 15 | Constructive Comment Extraction from Japanese YouTube Shorts: A Dataset and Empirical Study | Siyuan Feng; Luecheng Wang; Koyo Ogura; Yuma Iwamoto; Seinosuke Sato; Yuki Kometani; Masaki Itabashi; Shintaro Ozaki; Yusuke Sakai; Shogo Matsuno; Hidetaka Kamigaito; Katsuhiko Hayashi; Ryoma Obara; Sho Takase; Taro Watanabe | Siyuan Feng |
| 51 | ARR-Dv2: New Data from ACL Rolling Review and its Potential to Improve Reviewing in the ACL Community | Atnafu Lambebo Tonja; Sheng Lu; Nils Dycke; Dirk Hovy; Koen Dercksen; Lizhen Qu; Xiaodan Zhu; Thamar Solorio; Iryna Gurevych; Margot Mieskes | Thamar Solorio |
| 78 | Auto-AdvER: Disentangling Condition, History, and Commercial Offers in Automotive Advertisements | Filippos Ventirozos; Ioanna Nteka; Tania Nandy; Jozef Bača; Charlie Roadhouse; Peter A. Appleby; Matthew Shardlow | Filippos Ventirozos |
| 90 | VIDA: A Dataset for Visually Dependent Ambiguity in Multimodal Machine Translation | Jingheng Pan; Xintong Wang; Longyue Wang; Liang Ding; Weihua Luo; Chris Biemann | Jingheng Pan |
| 136 | FahMai-TeleBench: A Thai Grounded Tool-Use Benchmark for the Deployable Model Tier | Nutchanon Yongsatianchot; Piyalitt Ittichaiwong; Jitkapat Sawatphol; Tichanat Ruangsiri | Nutchanon Yongsatianchot |
| 138 | ThaiEditBench: A Mechanism-Typed, Length-Stratified Benchmark for Thai Orthographic Error Correction | Nutchanon Yongsatianchot; Piyalitt Ittichaiwong; Kanyakorn Veerakanjana | Nutchanon Yongsatianchot |
Session 1.2: Interpretability and Analysis of Models for NLP 2
Friday, November 6, 11:00-12:30 · MR 3
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 453 | Do LLM Embedding Spaces Recover Expert Structure? | Yixuan Zhu; Zhenke Duan; Fanghen Li | Zhenke Duan |
| 517 | Multidimensional Consistency Improves Reasoning in Language Models | Huiyuan Lai; Xiao Zhang; Malvina Nissim | Huiyuan Lai |
| 523 | What Changes in Hidden States When Model Merging Hurts Task Performance? | Canasai Kruengkrai; Koichiro Yoshino | Canasai Kruengkrai |
| 699 | RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty | Gukhyeon Lee; SangKeun Lee | Gukhyeon Lee |
| 719 | Predicting Mergeability of Language Model Domain Experts | Ervin Dervishaj; Quynh Do; Giannis Karamanolakis; Anna Rumshisky; Salma Sohrabi-Jahromi; Judith Gaspers | Ervin Dervishaj |
| 761 | Information-Theoretic Design of Sparse Autoencoder-Based Steering | Hirofumi Morise | Hirofumi Morise |
Session 1.3: NLP Applications and Human-AI Interaction 1
Friday, November 6, 11:00-12:30 · MR 4
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 122 | A Multilingual Evaluation of LLM-Based High-School Mathematics Assistance Across Indian Languages | Yash Kumar; Subhajit Roy | Yash Kumar |
| 188 | Conversational Intelligent Tutoring Systems: Evolution, Taxonomy, and Pedagogical Frontiers | Zhengyuan Liu; Stella Xin Yin; Li Zhu; Xiaoman Wang; Yunshi Lan; Nancy F. Chen | Zhengyuan Liu |
| 261 | DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text | Mohamed Mady; Yupei Li; Johannes Reschke; Björn Schuller | Mohamed Mady |
| 344 | MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring | Woojin Lee; Woo Yoon Kyu; Jinah Kim; Hyeok-Min Gwon; Jin-Xia Huang | Woojin Lee |
| 424 | CAFE: Caption-Anchored Feature Enrichment and Evidence Routing for Multimodal Sarcasm Detection | Puchu Zeng; Yun Luo; qianqian li; Yanzhou Ma; Liu Junyi; SongFengxuan; chonghuifang | Yun Luo |
| 563 | “Do You Truly Love Me?” Benchmarking LLM Capability on Hierarchical Pragmatic Tactic Conversations | Peter Q. Chen; Pangjing Wu; Zhuohang Jiang; Xiaodong Li; Peter H. F. Ng | Peter Q. Chen |
Session 1.4: Ethics, Bias, and Fairness
Friday, November 6, 11:00-12:30 · MR 5
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 19 | Decomposing LLM Advice Sycophancy: Content, Style, and Framing Drive Distinct Response Dimensions | Jaya Singh; Verena Kaynig-Fittkau | Jaya Singh |
| 40 | MortalMATH: Evaluating the Conflict Between Reasoning Objectives and Emergency Contexts | Etienne Lanzeray; Stephane Meilliez; Malo Ruelle; Damien Sileo | Damien Sileo |
| 61 | HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment | Omar El Herraoui; Ali Mekky; Preslav Nakov; Yuxia Wang | Omar El Herraoui |
| 549 | KoEVD: A Korean Benchmark for Metadata-Conditioned Multi-Stage LLM Safety Evaluation | San Kim; Wonjung kim; Heesoo Kwon; Jae Hee Yang | San Kim, Heesoo Kwon |
| 604 | A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem | Laizhen Li; Xuan Wang; Peicheng Zhao; Juanjuan Zhao; Kejiang Ye; Cheng-zhong Xu; Xitong Gao | Xitong Gao |
| 744 | Does Fairness Survive Model Adaptation in Legal Judgment Prediction? | Sarah Kamoun; Parth Patel; Faezeh Ensan | Sarah Kamoun |
Session 1.5: Generation and Dialogue
Friday, November 6, 11:00-12:30 · MR 6
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 119 | Mitigating the Impact of Glitch Tokens via Targeted Retokenization | Muhammad Alif Al Hakim; Dmitrii Kuzmin; Carlos Javier Galán Zavala; Tatsuya Hiraoka; Munachiso Samuel Nwadike; Ayana Niwa; Marco Cognetta; David Pohl; Kentaro Inui | Muhammad Alif Al Hakim |
| 160 | DIAM: Discourse Interaction and Addressee Modeling for Malaysia Hansard | Goh Kun Shun; Mohan Raj; Lay-Ki Soon; Wern Han Lim; Ian K. T. Tan | Mohan Raj Chanthran |
| 241 | Read the Room Before Your Model Generates | Muyao Kong; Zhihao Lin | Muyao Kong |
| Zhihao Lin | |||
| 302 | Grounding What Users Care About: Multi-Aspect Personalized Modeling from Implicit Preferences | Jiin Park; Misuk Kim | Jiin Park |
| 511 | Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization | Joonho Yang; Seunghyun Yoon; Hwan Chang; Byeongjeong Kim; Hwanhee Lee | Joonho Yang |
| 700 | Transferable Structural Priors in Continuous Diffusion Language Models | Hao Li; Man Fung Zhuo; Xinqi Liu; Jiayu Wu; Yifan Hong | Hao Li |
Session 2.1: Resources and Evaluation 2
Friday, November 6, 15:30-17:00 · Muhe B+C
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 170 | JudgeMoE: Distributional Aggregation for LLM-as-a-Judge | Yiqi Liu; Joseph James; Yang Wang; Kun Zhao; Chenghao Xiao; Chenghua Lin | Yiqi Liu |
| 194 | Are Many Tasks Necessary for General LLM Evaluation? A Matrix Completion View of Benchmark Redundancy | Kohei Tsuji; Yusuke Sakai; Hidetaka Kamigaito; Taro Watanabe | Kohei Tsuji |
| 245 | T2MBench: Evaluating Text-to-Motion Generation under Diverse Language Instructions | Bin Yang; Rong OU; Weisheng Xu; Jiaqi Xiong; Xintao Li; Taowen Wang; Luyu Zhu; Yuetong Fang; Xu Jiang; Jing Tan; Renjing Xu | Bin Yang |
| 258 | SG-LegalCite: A Principle-Augmented Benchmark for Legal Citation Retrieval in Singapore Law | LEE YUEH ERN SHANNON; Kaidong Feng; Yingpeng Du; Lee En Jia Chloe; Zhu Sun | Shannon Lee Yueh Ern |
| 299 | SEA-NLI: Language Inference as a Lens into Southeast Asian Cultural Understanding | Peerawat Chomphooyod; Yosephine Susanto; Jian Gang Ngui; Attapol Rutherford; Alham Fikri Aji; Sarana Nutanong; Can Udomcharoenchaikit; Peerat Limkonchotiwat | Peerat Limkonchotiwat, Can Udomcharoenchaikit |
| 341 | Penalty-Framed No-Valid-Option MCQA: Analyzing LLM Abstention under Invalid Choices | Jinhyeok Kim; Hye-Young Jung | Jinhyeok Kim |
Session 2.2: Multimodality and Language Grounding
Friday, November 6, 15:30-17:00 · MR 3
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 163 | Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy | Shujian Gao; Yuan Wang; Jiangtao Yan; Zuxuan Wu; Yu-Gang Jiang | Shujian Gao |
| 267 | MMA: Multimodal Memory Agent | Wanru Cheng; Yihao Lu; Zeyu Zhang; Hao Tang | Yihao Lu |
| 455 | The Model Knows Where to Look: Visual-Grounding-Guided Head Suppression for Mitigating Hallucination in LVLMs | Mong Yuan Sim; Wei Emma Zhang; Xiang Dai; Biaoyan Fang | Mong Yuan Sim |
| 583 | CGVR: Contradiction-Guided Visual Reasoning for Mitigating Hallucinations in Multimodal Large Language Models | Haoran Ding; Wanqi Zhou; Lei Xing; Lujuan Dang; Kaizhong Zheng; Badong Chen | Haoran Ding |
| 668 | CircuitPile: A Data Synthesis Framework for Enhancing Multimodal LLMs’ Perception on Circuit Schematics | Hongyu Chang; Xinyue Li; Huanyong Liu; Feng Zhang; Yuhui Yin | Hongyu Chang |
| 731 | The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm | Karan Goyal | Karan Goyal |
Session 2.3: NLP Applications and Human-AI Interaction 2
Friday, November 6, 15:30-17:00 · MR 4
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 596 | A Framework for Evaluating AI-Generated Creativity: Human–LLM Agreement in Story Evaluation | Pharath Sathya; Yin Jou Huang; Fei Cheng | Pharath Sathya |
| 602 | Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation with a Universal Evaluation Framework | Zheye Deng; Chunkit Chan; Tianshi Zheng; Wei Fan; Weiqi Wang; Yangqiu Song | Zheye Deng |
| 648 | Reasoning-Based Personalized Generation for Sparse Users | Bo Ni; Branislav Kveton; Samyadeep Basu; Subhojyoti Mukherjee; Leyao Wang; Franck Dernoncourt; Sungchul Kim; Seunghyun Yoon; Zichao Wang; Ruiyi Zhang; Puneet Mathur; Jihyung Kil; Jiuxiang Gu; Nedim Lipka; Yu Wang; Ryan A. Rossi; Tyler Derr | None |
| 732 | Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications | Aayush Acharya; Qi Zhang; Eduard Dragut; Longin Jan Latecki | Aayush Acharya |
| 752 | Breaking Bureaucracy: Evaluating open-source LLMs for legal document review | Farrukh Baratov; Niki van Stein; Suzan Verberne | Farrukh Baratov |
| 799 | From Preferences to Scores: Semi-Supervised Multi-Trait Essay Scoring with LLM Pairwise Preferences and Few Human Anchors | Takumi Shibata; Yuichi Miyamura | Takumi Shibata |
Session 2.4: Computational Social Science and Cultural Analytics
Friday, November 6, 15:30-17:00 · MR 5
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 35 | WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias | Kento Haneda; Yosuke Kishinami; Ryo Fujii; Keisuke Sakaguchi; Makoto Morishita | Kento Haneda |
| 56 | Fairness in Prompting: How Demographic Variations Affect Language Model Outputs | Ryandito Diandaru; Gleb Kuzmin; Muhammad Dehan Al Kautsar; Zeerak Talat; Xudong Han; Haonan Li; Tatsuki Kuribayashi; Artem Shelmanov; Timothy Baldwin; Fajri Koto | Ryandito Diandaru |
| 219 | Learning What Is Said, Not How: Stance-Contrastive Learning for Generalizable Hate Speech Detection | yucheng lin; Dan Kienast; Jiaojiao Jiang | yucheng lin |
| 364 | Automatic Evaluation of Mental Health Stigma in Online Communication | Naomi Baes; Jemima Kang; Nick Haslam; Chris Groot; Alsa Wu; Luc Raszewski; Yulia Otmakhova | Jemima Kang |
| 447 | Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games | Neemesh Yadav; Yihuai Lan; Shan Dong; Mai Hieu Hien; Palakorn Achananuparp; Jing Jiang; Ee-Peng Lim | Palakorn Achananuparp |
| 491 | Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity | Jaeyoon Jung; Yejun Yoon; Kunwoo Park | Kunwoo Park |
Session 2.5: Efficient Methods and Machine Learning for NLP 1
Friday, November 6, 15:30-17:00 · MR 6
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 16 | PRC: An Efficient and Unified Framework for Evaluating Robustness and Controllability of Large Language Models on Few-shot Prompt Variations | Chunpeng Ma | Chunpeng Ma |
| 96 | Supportive Token Revealing for Fast Diffusion Language Model Decoding | Giries Abu Ayoub; Mario Barbara; Lluís Pastor-Pérez; Tanja Bien; Aneesh Barthakur; Alaa Maalouf; Loay Mualem | Giries Abu Ayoub |
| 107 | Token-Level On-Policy Contrastive Distillation Without Full Rollouts | Jian Yang; Chern Hong Lim; Thuy-Trang Vu | Jian Yang |
| 118 | EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering | Thao Do; Dinh Phu Tran; An Vo; Seon Kwon Kim; Daeyoung Kim | Thao Do |
| 237 | Less Random, More Incoherent: Greedy Hadamard Alignment for LLM Quantization | Yun Ye; Zhaoqi Wu; Xueshu Wang; Cong Zhang; Zhu Yongbo; Zhonghua Sun; BERYL XU | Yun Ye |
| 342 | mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT | Woosung Koh; Jeyoung Jeon; Youngjin Song; Yujin Cheon; Soowon Oh; Jaehyeong Choi; Se-Young Yun | Jeyoung Jeon |
Session 3.1: Resources and Evaluation 3
Saturday, November 7, 10:30-12:00 · Muhe B+C
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 361 | LKValues: Aligning Large Language Models with Sri Lankan Societal Values | Nethmi Muthugala; Supryadi; Surangika Ranathunga; Nisansa de Silva; Ruijie Tao; Ovindu Gunatunga; Pengyun Zhu; Shaowei Zhang; Jingting Zheng; Deyi Xiong | Nethmi Muthugala (M.W.N.N.Muthugala) |
| 381 | A Reliability Audit of Aggregated MTEB Scores: Coverage Asymmetry and Language-Specific Rank Inversions Across 17 Languages | Archit Rastogi | Archit Rastogi |
| 402 | DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning | Haoxiang Sun; Lizhen Xu; Bing Zhao; Wotao Yin; Wei Wang; Boyu Yang; Rui Wang; HU WEI | Haoxiang Sun |
| 416 | VERGE: Verification-Enhanced Generation of Multi-Hop Evaluation Datasets for Task-Specific RAG | Kyosuke Morita | Kyosuke Morita |
| 421 | Auditing PEFT Claims: A Stability Probe Unifying Three LoRA-Variant Fragility Patterns | Suan Lee; JaeSeong Kim | Suan Lee |
| 422 | Memorization or Extraction? Auditing LLM-Based Recovery of Scientific Assumptions | Suan Lee; JaeSeong Kim | Suan Lee |
Session 3.2: LLM Agents and Learning
Saturday, November 7, 10:30-12:00 · MR 3
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 108 | A Survey of the Training Process of LLM-Based Agents | Zhisong Zhang; Lemao Liu; Tianqing Fang; Deng Cai; Jiahao Xu | Zhisong Zhang |
| 227 | Knowing When to Critique: Task-Adaptive Metacognitive Regulation for Reliable LLM Reasoning | Xinmeng Hou; Ziting Chang; Zhouquan Lu; Bohao Qu; Liang Wan; Wei Feng; Hai Hu; Qing Guo | Ziting Chang |
| 345 | YouRA: A Persistent-State Architecture for Evidence-Traceable Autonomous Research Agents | Woo Yoon Kyu; Woojin Lee; Jin-Xia Huang | Yoonkyu Woo |
| 589 | JanusPO: Asymmetric Clip and KL for Entropy-Stable Group Policy Optimization in Tool-Augmented LLM Reasoning | Hao Li; Man Fung Zhuo; Guangxin Wu; Yusen Wu; Jiayu Wu | Hao Li |
| 591 | HorizonBench: Evaluating Ideation Agents on Future Scientific Discoveries | Markus Flicke; Haoyu He; Kashyap Chitta; Yong Cao; Andreas Geiger | Yong Cao |
| 637 | Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval | Sana Ayromlou; Purvi Sehgal; Pradyumna Narayana | Pradyumna Narayana |
Session 3.3: Clinical and Biomedical Applications
Saturday, November 7, 10:30-12:00 · MR 4
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 5 | Generating Linguistically Diverse and Semantically Faithul Patient Reports | Alejandra Lorenzo; Adrien Coulet; Claire Gardent | Adrien Coulet |
| 139 | EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models | J. Ben Tamo; Yuxing Lu; Benoit Louis Marteau; Micky C. Nnamdi; May Dongmei Wang | Yuxing Lu |
| 221 | Cleaner Speech, Weaker Generalization: Revisiting Pitt-Derived Benchmarks for Alzheimer’s Disease Detection | Luqi Sun; Shreeram Suresh Chandra; Lin Zhang; You-Jin Li; Brian MacWhinney; Yu Tsao; Emily Mower Provost; Berrak Sisman | Luqi Sun |
| 222 | CARE-Bench: Benchmarking Patient-Facing LLM Triage | Yining Hua; Hongbin Na; Cyrus Ayubcha | Hongbin Na |
| 667 | Lay-Language and Cross-Lingual Disparities in LLM Medical Diagnosis: A Case Study in Rheumatological Skin Conditions | Grayson Hubbell; Yifei Zhang; Saksham Khatwani; Sriram Sankaranarayanan; Indira Sriram; Maria Leonor Pacheco | Grayson Hubbell |
| 703 | Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data | Zhenyu Lu; Mahyar Abbasian; Amir M. Rahmani | Zhenyu Lu |
Session 3.4: Interpretability and Analysis of Models for NLP 1
Saturday, November 7, 10:30-12:00 · MR 5
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 65 | Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages | Lyzander Marciano Andrylie; Inaya Rahmanisa; Mahardika Krisna Ihsani; Alfan Farizki Wicaksono; Haryo Akbarianto Wibowo; Alham Fikri Aji | Lyzander Marciano Andrylie |
| 144 | Signatures of Steerability in Activation Space of Language Models | Prajjwal Bhattarai; Tuka Alhanai | Prajjwal Bhattarai |
| 259 | Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models | Lingfang Li; Procheta Sen; Shubham Das; Danushka Bollegala | Lingfang Li |
| 271 | Empathy Is Not the Scapegoat for Declines in Factuality and Reliability | Kanwal Mehreen; Letian Shi; Deheng Zhang; Yuxia Wang | Yuxia Wang |
| 318 | Mechanistic Evidence Routing in Transformers: Margin-Gated Intervention for Retrieval-Conflict Hallucination | Sridurgesh Ravichandran | Sridurgesh Ravichandran |
| 417 | Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax | Zhenyan Lu; He Wang; Xiaohui Huang | Zhenyan Lu |
Session 3.5: Machine Translation and Phonology
Saturday, November 7, 10:30-12:00 · MR 6
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 52 | Improving Japanese-English Patent Claim Translation via Reasoning and GRPO with Syntactic Reward | Shogo Tsujimoto; Katsuki Chousa; Masaaki Nagata; Ryohei Sasano | Shogo Tsujimoto |
| 191 | Reference-Grounded Data Curation for Instruction-Following Thai-English Machine Translation | Thodsaporn Chay-intr; Krittapad Harnchang; Mahannop Thabua; Kobkrit Viriyayudhakorn; Thanaruk Theeramunkong | Thodsaporn Chay-intr |
| 201 | Video-guided Machine Translation for Indic Languages | Pinaki Das; Srikar Ayyagari; Raj Dabre; Thuy-Trang Vu; Virendra Singh; Pushpak Bhattacharyya; Gholamreza Haffari | Pinaki Das |
| 207 | Lexically Stable but Semantically Improvable: On the Editability of Machine Translation Drafts for LLM Post-Editing | Tianlin Xiao; WenHan Chao | Tianlin Xiao |
| 235 | ToneCL:Contrastive Learning for Few-Shot Syllable-Level Tone Classification | Qisheng Liao; Youngah Do | Qisheng Liao |
| 571 | Does Translation Preserve Who You Are? Quantifying Speaker Personality Consistency Across Languages | Xinger Fu; Masaaki Nagata; Chenhui Chu | Xinger Fu |
Session 4.1: Resources and Evaluation 4
Sunday, November 8, 10:30-12:00 · Muhe B+C
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 459 | PersonaPath: A Benchmark for Knowledge-Centric Personalized Learning Path Planning | Yu Liu; Zeming Liu; Tianle Zhang; Zihao Cheng; Yuhang Guo; Kehai Chen; Min Zhang; Yunhong Wang; Haifeng Wang | Yu Liu |
| 461 | Multicultural Spyfall: Assessing LLMs through Dynamic Multilingual Social Deduction Game | Haryo Akbarianto Wibowo; Alaa Elsetohy; Qinrong Cui; Alham Fikri Aji | Haryo Akbarianto Wibowo |
| 464 | Benchmarking Fine-Grained Readability Explanations for Arabic | Nour Rabih; Khalid N. Elmadani; Hanada Taha; Nizar Habash | Nour Rabih |
| 468 | Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation | Mario Sanz-Guerrero; Minh Duc Bui; Manuel Mager; Katharina von der Wense | Mario Sanz-Guerrero |
| 476 | Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction | Tianyun Zhong; Guozhao Mo; Yanjiang Liu; Yihan Chen; Lingdi Kong; Xuanang Chen; Yaojie Lu; Hongyu Lin; Shiwei ye; Shanshan Jiang; Bin Dong; Le Sun; Ben He; Xianpei Han | Tianyun Zhong |
| 519 | CriticGen: Generation-Aware Evaluation as Actionable Feedback | Huifang Du; Zecheng Zuo; Sen Wang; Haofen Wang; Yehui Yang | Zecheng Zuo |
Session 4.2: Language Modeling
Sunday, November 8, 10:30-12:00 · MR 3
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 109 | CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning | Rahul Markasserithodi; Aditya Joshi; Yuekang Li; Ishmanbir Singh; Chris Yoo; Alan Niu | Rahul Markasserithodi |
| 243 | Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks | Tian Gao; Zhipeng Xie; Yuhao Wu; Junhua Liu; Xin Fang | Zhipeng Xie |
| 559 | CLEF: Closed-Loop Error Feedback for Multi-Bit Watermarking in Short LLM-Generated Text | Jing Wang; Kejun Qian; Pengyu Xiong; Qiankun Zhang; Yi Yang; Jing Fan | Kejun Qian |
| 567 | Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting | Kihyun Kim; Hee-Seon Kim; Wonjun Lee; Changick Kim | Kihyun Kim |
| 657 | LLM-as-RNN: A Recurrent Language Model for Memory Updates and Sequence Prediction | Yuxing Lu; J. Ben Tamo; Jinrui Fang; Weichen Zhao; Nan Sun; Xukai Zhao; Yishan Zhong; Wenqi Shi; Jinzhuo Wang; May Dongmei Wang | Yuxing Lu |
| 776 | See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models | Yunzhen He; Hiroaki Yamagiwa; Hidetoshi Shimodaira | Yunzhen He |
Session 4.3: Efficient Methods and Machine Learning for NLP 2
Sunday, November 8, 10:30-12:00 · MR 4
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 410 | S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching | Jialong Han; You Wu; Kewei Tu | Jialong Han |
| 471 | ROCOB: Dual-Manifold Alignment with Optimal Budgeting for Training-Free PTQ Recovery | Haoqi Yang; Teng Xiao; Zuchao Li; Hao Huang; Lefei Zhang; hai zhao | Haoqi Yang |
| 497 | When Token Supervision Fails: Segment-Level On-Policy Distillation for Long-Horizon Agents | Jialong Liu; Zuchao Li; Yuling Shi; Lefei Zhang; Baoyuan Qi; hai zhao | JIALONG LIU |
| 530 | Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations | Jungwon Park; Changin Choi; Jimyeong Kim; Nojun Kwak; Wonjong Rhee | Jimyeong Kim |
| 640 | Influcoder: Distilling Decoders’ Gradient Influence Rankings into an Encoder for Data Attribution | Dimitri Kachler; Damien Sileo; Pascal Denis | Dimitri Kachler |
| 781 | Not All Tokens Are Equally Important: Auditing and Compressing Redundancy in LLM Reasoning | Nguyen-Khang Le; Dieu-Hien Nguyen; Truong Dinh Do; Le-Minh Nguyen | Dieu-Hien Nguyen |
Session 4.4: Semantics and Linguistic Structure
Sunday, November 8, 10:30-12:00 · MR 5
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 7 | Dynamics of Meaning: Towards the Evaluation of Diachronic Semantic Change in Sinhala | Nevidu Jayatilleke; Nisansa de Silva | Nevidu Jayatilleke |
| 13 | Are Linguistic and Arithmetic Circuits Dissociated in LLMs? | Riku Kisako; Tatsuki Kuribayashi; Ryohei Sasano | Riku Kisako |
| 384 | WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution | Yi Zhou; Kiamehr Rezaee; Danushka Bollegala; Mohammad Taher Pilehvar; Jose Camacho-Collados | Yi Zhou |
| 451 | Edit Policy-Aligned Text Simplification | Xuanxin Wu; Yuki Arase; Masaaki Nagata | Xuanxin Wu |
| 486 | You Can Create Words Rather Than Just Detect Them: Towards A New Paradigm of Chinese Neologisms | Qiliang Liang; Hansi Wang; Yue Wang; Yang Liu | Qiliang Liang |
| 575 | Cross-Lingual Semantic Fusion: Towards Universal Sentence Representations via LLMs | Zhen Hu; Zhu Liu; Ying Liu | Zhen Hu |
Session 4.5: Question Answering and Retrieval
Sunday, November 8, 10:30-12:00 · MR 6
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 81 | DBRAG: Multi-Table Retrieval-Augmented Generation for Complex Database Queries | Prince Larbi Ampofo; Ryoji Kubo; Djellel Difallah | Djellel Difallah |
| 133 | When the Correct Law Still Fails: A Diagnostic Benchmark for Law-in-Force Retrieval in Versioned Legal RAG | Yuchen Yao; Yiran HU; 张凯翔; Yixin Su; Jiani Ge; Yun Liu | Yuchen Yao |
| 277 | CoMMA: Conflict-Aware Read-Time Control for Conversational Memory QA | Zixiao Wang; Xingbo Du; Duzhen Zhang; Le Song | Zixiao Wang |
| 399 | Training-Free Residual-Guided Retrieval for Multi-hop KGQA with Single-Step LLM Inference | Keito Sei; Sunil Kumar Maurya; Yohei Kobashi; Yutaka Matsuo | Keito Sei |
| 516 | CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification | Chenshuo Pan; Yu Zhao; Jie Zhang; Changzai Pan; Jiayi Liang; Yujie Mao; Zhenhe Wu; Shuangyong Song; Yongxiang Li; Zhongjiang He | Yu Zhao |
| 528 | STRIDE: Structural Reasoning for In-context Demonstration Extraction in Multi-hop Question Answering | Shiwei Chen; Bin Liang; Hui Wang; Yue Yu; Kam-Fai Wong; Ruifeng Xu | Keyang Ding |
Session 5.1: Resources and Evaluation 5
Sunday, November 8, 14:00-15:30 · Muhe B+C
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 531 | ArtHopQA: Diagnosing Hidden-Chain Recovery in Artwork Question Answering | Xuefeng Wei; Xuan Zhou; Yuta Kato; Shintaro Ozaki; Kazuki Hayashi; Yusuke Sakai; Hidetaka Kamigaito; Katsuhiko Hayashi; Taro Watanabe | Yusuke Sakai |
| 547 | K-Prism: A Korean Diagnostic Benchmark for Multi-faceted Hallucination in Vision-Language Models | Min Hyuk Kim; DONG HYOK SHIN; Jimi Lee; Jin Yea Jang | Min Hyuk Kim |
| 548 | KoMMERCE: A Korean Multimodal and Multitask Evaluation Benchmark for Reliable Conversational E-commerce Agents | Byunggill Joe; San Kim; Minyoung Jung; DONG HYOK SHIN; Yu-Jeong Sung; Saim Shin | Byunggill Joe |
| 584 | KBS: A Korean Benchmark Suite for Foundation Model Evaluation | Yeonkyoung So; Jongmin Kim; Sungmok Jung; Gyuseong Lee; Sangho Kim; Jongyeon Park; Joonhak Lee; Seho Pyo; Gyeongje Cho; Seorin Kim; Jisoo Kim; Suyoung Park; Hyunji M. Park; Yelim Ahn; Yeongho Seo; Jaejin Lee | Yeonkyoung So |
| 730 | What Improves During Pretraining? Temporal Stability Reveals Uneven Learning in LLM Benchmarks | Chang Su; Bin Wu; Emine Yilmaz; Yao Lu | Chang Su |
| 778 | Back to Basics, Powered by Data: Character-Level Transformers for Robust Chinese Machine-Generated Text Detection | Shengjie Xu; Zhenghao Gao; Rujie Dai; Zijing Li; Xiaoyang Xie; Zehua Lyu | Shengjie Xu |
| Zhenghao Gao |
Session 5.2: Multimodal, Medical, and Embodied Models
Sunday, November 8, 14:00-15:30 · MR 3
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 315 | Routing-Based Continual Learning for Multimodal Large Language Models | Jay Mohta; Kenan E. Ak; Gwang Gook Lee; Dimitrios Dimitriadis; Yan Xu; Mingwei Shen | Gwang Gook Lee |
| 689 | Latent Prediction Needs Alignment: A Controlled Study of Joint-Embedding Predictive Vision–Language Learning | Mohammad Kohankhaki; Daniel Kusuma; Shirin Salehi; Carsten Kamp; Sigrid Brell-Cokcan; Anke Schmeink | Mohammad Kohankhaki |
| 321 | Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models | Farhad Nooralahzadeh; Benjamin Gundersen; Nicolas Deperrois; Hidetoshi Matsuo; Mizuho Nishio; Thomas Frauenfelder; Ahmed Allam; Christian Bluethgen; Michael Moor; Michael Krauthammer | Farhad Nooralahzadeh |
| 613 | MedHal: A Synthetic Dataset for Medical Hallucination Detection | Fabrice Lamarche; Gaya Mehenni; Neshat Elhami Fard; Odette Rios-Ibacache; Li Ming Wang; John Kildea; Amal Zouaq | Fabrice Lamarche |
| 774 | Encoded but Not Express: Probing Subtle Speech-Conditioned Emotion in Large Audio Language Models | Jingxi Liang; Pengze Guo; Qifeng Wang; Zhiwen Xie; Yujia Huo; Derek F. Wong | Pengze Guo |
| 777 | Amortizing Self-Correction for Continual Embodied Adaptation | Woo Kyung Kim; Jooyoung Kim; Minjong Yoo; Honguk Woo | Woo Kyung Kim |
Session 5.3: Information Extraction, Retrieval, and Code
Sunday, November 8, 14:00-15:30 · MR 4
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 44 | Escaping the Tokenizer Trap: Probabilistic Semantic Routing for Dense Retrieval in Specialized Domains | Siu Hin Ng | Siu Hin Ng |
| 586 | DisamKB: Direct Construction of Disambiguated Knowledge Bases from Large Language Models | Yujia Hu; Tuan-Phong Nguyen; Simon Razniewski | Yujia Hu |
| 608 | Target-Conditioned Gating for Many-to-Many Argument Assignment in Document-Level Event Extraction | Junru Liao; Haoran Wang; Xuanjing Huang; Yatian Shen | Haoran Wang |
| 696 | Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction | Mikel Zubillaga; Oscar Sainz; Oier Lopez de Lacalle; Eneko Agirre | Mikel Zubillaga |
| 705 | Policy-Conditioned Constrained Decoding for Column-Level Access Control in Text-to-SQL | Miyamoto Ryoto; Xin Fan; Hayato Yamana | Ryoto MIYAMOTO |
| 714 | Domain-Agnostic Neural Topic Modeling with Contextual Token-Level Semantic Graph Representation | Seung-Won Seo; Won Ik Cho; Yongmin Yoo | Seung-Won Seo |
Session 5.4: Multilingualism and Cross-Lingual NLP
Sunday, November 8, 14:00-15:30 · MR 5
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 137 | Composing Within Constraints: A Benchmark for Thai Classical Poetry in Large Language Models | Nutchanon Yongsatianchot; Phuvis Kerdpramote | Nutchanon Yongsatianchot |
| 296 | DuDi: Dual-Signal Distillation with Cross-Lingual Verbalizer | Patomporn Payoungkhamdee; Tinnakit Udsa; Jian Gang Ngui; Sarana Nutanong; Alham Fikri Aji; Peerat Limkonchotiwat | Tinnakit Udsa |
| 388 | MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation | Tianyi Xu; Kosei Uemura; Alfred Malengo Kondoro; Catherine Nana Nyaah Essuman; Tadesse Destaw Belay; Ifeoma Okoh; Ganiyat Afolabi; Ayodele Awokoya; David Ifeoluwa Adelani | Tianyi Xu |
| 389 | IndicIFEval: A Benchmark for Verifiable Instruction-Following Evaluation in 14 Indic Languages | Thanmay Jayakumar; Mohammed Safi Ur Rahman Khan; Raj Dabre; Ratish Puduppully; Anoop Kunchukuttan | Thanmay Jayakumar |
| 554 | CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks | Peiqin Lin; Chenyang Lyu; Wenjiang Luo; Haotian Ye; Md Mehrab Hossain; Chunlan Ma; Shaoxiong Ji; Younes Samih; Bo Zeng; Fan Jiang; Yuanbin Cao; DILDA DUISENBEK; Adrian Neo Sau Xun; POZDNIAKOVA DARIA; MISEVICH LIUBOU; Marinković Nevena; Ngoc Gia Linh Nguyen; THI KHANH LINH DO; SARAKMATAK SOPHY; Baotian Hu; Guanhua Chen; Gongbo Tang; Alham Fikri Aji; Longyue Wang; Weihua Luo | Peiqin Lin |
| 695 | Toward LLMs Beyond English-Centric Development | Sho Takase; Ukyo Honda | Sho Takase |
Session 5.5: Sentiment, Culture, and Model Behavior
Sunday, November 8, 14:00-15:30 · MR 6
| # | Paper | Authors | Presenter |
|---|---|---|---|
| 566 | What Makes User Reactions Useful for Fake News Detection? | Yassine Toughrai; David Langlois; Smaili | Yassine Toughrai |
| 34 | Argument Summarization: A Unified Task Definition, Taxonomy, and Survey | Zhiqiang Shi; Oana Cocarascu | Zhiqiang Shi |
| 478 | Explainable End-to-End Argument Mining with Toulmin‑Structured Explanations | Zhiqiang Shi; Oana Cocarascu | Zhiqiang Shi |
| 14 | Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages | Lucinda Laurent; Muhammad Dehan Al Kautsar; Alfan Farizki Wicaksono; Fajri Koto | Lucinda Laurent |