iiinova — where your digital self keeps evolving

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Adithya Bhaskar, Jeffrey Cheng, Danqi Chen: Language Models that Play Chess and Explain Their Moves arxiv.org/abs/2610.03695 arxiv.org/pdf/2610.03695 arxiv.org/html/2610.03695

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Darian Lee, Shannon Rumsey, Jack St. Clair, Xinyi Tang, Aditya Bansal, Yuanming Shi: FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs arxiv.org/abs/2610.03625 arxiv.org/pdf/2610.03625 arxiv.org/html/2610.03625

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

David L. Condrey: Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting arxiv.org/abs/2610.03567 arxiv.org/pdf/2610.03567 arxiv.org/html/2610.03567

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

David L. Condrey: Writerslogic at PAN 2026: Process over Content for Robust Detection under Domain Shift arxiv.org/abs/2610.03565 arxiv.org/pdf/2610.03565 arxiv.org/html/2610.03565

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Habib, Adewumi, Al-Azzawi, Liwicki, Barney: Author Representation Strategies for Zero-Shot Authorship Attribution: A Comparative Study of LLM-Based and Embedding-Based Approaches arxiv.org/abs/2610.03531 arxiv.org/pdf/2610.03531 arxiv.org/html/2610.03531

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Teng Lin, Xinyu Liu, Nan Tang: Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation arxiv.org/abs/2610.03525 arxiv.org/pdf/2610.03525 arxiv.org/html/2610.03525

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Chenglei Shen, Haoyang Yao, Weijie Yu, Song Jin, Xiao Zhang, Jun Xu: Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation arxiv.org/abs/2610.03515 arxiv.org/pdf/2610.03515 arxiv.org/html/2610.03515

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Ghassabi, Rostami, Kashani, Hakim, Ebrahimi: Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models arxiv.org/abs/2610.03482 arxiv.org/pdf/2610.03482 arxiv.org/html/2610.03482

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Hang Gao, Wujiang Xu, Zhixing Zhang, Kai Mei, Jingyi Yang, Dimitris N. Metaxas: CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation arxiv.org/abs/2610.03421 arxiv.org/pdf/2610.03421 arxiv.org/html/2610.03421

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Mohsen Larni, Sobhan Ebrahimi Azar, Pouyan Nahed, Kazem Taghva: SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models arxiv.org/abs/2610.03329 arxiv.org/pdf/2610.03329 arxiv.org/html/2610.03329

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Demetris Paschalides, George Pallis, Marios D. Dikaiakos: To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation arxiv.org/abs/2610.03324 arxiv.org/pdf/2610.03324 arxiv.org/html/2610.03324

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Roham Zendehdel Nobari, Shayan Sooratgar: Shrome at Touch\'e: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality Extraction arxiv.org/abs/2610.03268 arxiv.org/pdf/2610.03268 arxiv.org/html/2610.03268

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Mingzhe Du, Luu Anh Tuan, Xiaobao Wu, Yichong Huang, Yue Liu, Dong Huang, Huijun Liu, Bin Ji, Jie M. Zhang, See-Kiong Ng: Collective Bias Mitigation via Model Routing and Collaboration arxiv.org/abs/2610.03240 arxiv.org/pdf/2610.03240 arxiv.org/html/2610.03240

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Rasha Albalawi, Nuha Albadi, Hamzah Luqman, Asma Yamani, Maram Kurdi, Saad Ezzini, Ahmed Ashraf, Maged Al-Shaibani, Nora Alturayeif: StanceEval 2026: The Second Stance Detection Shared Task arxiv.org/abs/2610.03215 arxiv.org/pdf/2610.03215 arxiv.org/html/2610.03215

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Jonghyun Song, Haewon Park, Jeonghoon Shim, Woojung Song, Yohan Jo: Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It arxiv.org/abs/2610.03195 arxiv.org/pdf/2610.03195 arxiv.org/html/2610.03195

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Tingzhu Bi, Ping Wang, Meng Ma: Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case arxiv.org/abs/2610.03190 arxiv.org/pdf/2610.03190 arxiv.org/html/2610.03190

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Aarav Singh, Animesh Pathak, Navyansh Singh: Hindsight-Guided Rationale Distillation for Rare Disease Diagnosis arxiv.org/abs/2610.03176 arxiv.org/pdf/2610.03176 arxiv.org/html/2610.03176

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Leonard Popp, Danni Liu, Supriti Sinhamahapatra, Jan Niehues: Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer arxiv.org/abs/2610.03163 arxiv.org/pdf/2610.03163 arxiv.org/html/2610.03163

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Oliver Hauck, Mario Sanz-Guerrero, Katharina von der Wense: Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation arxiv.org/abs/2610.03136 arxiv.org/pdf/2610.03136 arxiv.org/html/2610.03136

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Ilya Chekin, Vyacheslav Malyugin, Vladimir Chirkov, Mikhail Yurushkin: Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM Signals arxiv.org/abs/2610.03112 arxiv.org/pdf/2610.03112 arxiv.org/html/2610.03112

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Claudiu Creanga, Liviu Dinu: Ontological Instability and Statistical Amplification: The Paradox of "Humanizing" LLM-Generated Text arxiv.org/abs/2610.03110 arxiv.org/pdf/2610.03110 arxiv.org/html/2610.03110

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Valentino Maiorca, Walter Nelson, Francesco Locatello: Emergent Structure in the Marginal Attention Space of Language Models arxiv.org/abs/2610.03109 arxiv.org/pdf/2610.03109 arxiv.org/html/2610.03109

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Ang Li, Yue Lin, Feifei Kou, Zhan Su, Prayag Tiwari, Wenhao Li, Shuhui Zhu, Hongyuan Zha, Baoxiang Wang: Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning arxiv.org/abs/2610.03102 arxiv.org/pdf/2610.03102 arxiv.org/html/2610.03102

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Hanlu He, Harald Vilhelm Skat-R{\o}rdam, Ingvi \"Orn\'olfsson, Ivana Konvalinka: An automated pipeline for standardised speech-unit annotation in spontaneous dialogue arxiv.org/abs/2610.03078 arxiv.org/pdf/2610.03078 arxiv.org/html/2610.03078

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Claudiu Creanga, Ioachim Lihor, Liviu P. Dinu: Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models arxiv.org/abs/2610.03077 arxiv.org/pdf/2610.03077 arxiv.org/html/2610.03077

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Tiezheng Yu, Yuxin Jiang, Jinpeng Li, Shuning Sun, Fei Mi, Haoli Bai, Lifeng Shang: HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation arxiv.org/abs/2610.03063 arxiv.org/pdf/2610.03063 arxiv.org/html/2610.03063

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Donggyun Kim, Jack Lu, Chanwoo Kim, Mengye Ren, Seunghoon Hong: HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning arxiv.org/abs/2610.03039 arxiv.org/pdf/2610.03039 arxiv.org/html/2610.03039

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Huijuan Wang, Chufan Shi, Cheng Yang, Yaokang Wu, Taylor Berg-Kirkpatrick, Xuezhe Ma: Recursive Self-Improvement in Unified Multimodal Models arxiv.org/abs/2610.03002 arxiv.org/pdf/2610.03002 arxiv.org/html/2610.03002

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Huiqiang Rong, Haoran Luo, Hui Feng, Zhonghong Ou, Kaiwen Xue, Guoxin Zhang, Yifan Zhu: OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination arxiv.org/abs/2610.02999 arxiv.org/pdf/2610.02999 arxiv.org/html/2610.02999

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Tao Shi, Chaoyi Xiang, Qiongkai Xu, Jey Han Lau: OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models arxiv.org/abs/2610.02986 arxiv.org/pdf/2610.02986 arxiv.org/html/2610.02986

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Songtao Li, Yijia Zhang, Shidi Zhang, Jianyuan Yuan, Fengyu Zhang, Hongfei Lin: A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition arxiv.org/abs/2610.02970 arxiv.org/pdf/2610.02970 arxiv.org/html/2610.02970

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Li, Zhang, Yuan, Zhang, Zhang, Lin: Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble Method arxiv.org/abs/2610.02949 arxiv.org/pdf/2610.02949 arxiv.org/html/2610.02949

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Riju Marwah, Ritvik Garimella, Khusham Bansal, Atishay Jain, Amit Sheth: Output Language Confusion under Multilingual Prompt Contamination arxiv.org/abs/2610.02926 arxiv.org/pdf/2610.02926 arxiv.org/html/2610.02926

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Lin Tian, Marian-Andrei Rizoiu: Misinformation Without Triggers: From Factual Answers to Downstream Decisions arxiv.org/abs/2610.02886 arxiv.org/pdf/2610.02886 arxiv.org/html/2610.02886

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Monika Shah, Sudarshan Balaji, Somdeb Sarkhel, Sanorita Dey, Deepak Venugopal: Evaluating VQA in Vision Language Models using Cooperative Principles arxiv.org/abs/2610.02878 arxiv.org/pdf/2610.02878 arxiv.org/html/2610.02878

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Cong, Hahn, Gombert, Camus, Zehner, Drachsler, Kroehne: Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty arxiv.org/abs/2610.02877 arxiv.org/pdf/2610.02877 arxiv.org/html/2610.02877

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Akshay Jain, Edward Kim: Query-aware routing for Cross-lingual performance gains in Encoders arxiv.org/abs/2610.02875 arxiv.org/pdf/2610.02875 arxiv.org/html/2610.02875

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Vihindi Kotalawala, Pamoda Dilranga, Gayani Thoradeniya, Prasan Yapa: ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution arxiv.org/abs/2610.02873 arxiv.org/pdf/2610.02873 arxiv.org/html/2610.02873

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Li, Feng, Huang, Fu, Huo, Zhou, Yuan, Zhang, Qin: Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models arxiv.org/abs/2610.02856 arxiv.org/pdf/2610.02856 arxiv.org/html/2610.02856

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Yun-Ang Wu, Xanh Ho, Andre Greiner-Petter, Sunisth Kumar, Tian Cheng Xia, Florian Boudin, Akiko Aizawa: How Robust Is Multimodal Claim Verification to LLM Rewriting? arxiv.org/abs/2610.02841 arxiv.org/pdf/2610.02841 arxiv.org/html/2610.02841

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Aishik Nagar, Abhishek Vaidyanathan, Arun-Kumar Kaliya-Perumal, Elijah Tzen Hsuen Boey, Stefan Winkler: Clinical Concept Centers in LLMs arxiv.org/abs/2610.02829 arxiv.org/pdf/2610.02829 arxiv.org/html/2610.02829

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Ziyang Cheng, Yuhao Wang, Hongcheng Liu, Qimin Wu, Jingru Fan, Chen Qian, Yanfeng Wang, Yu Wang: Text-Centric Post-Training for Omni-Modal Reasoning arxiv.org/abs/2610.02819 arxiv.org/pdf/2610.02819 arxiv.org/html/2610.02819

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Naomi Baes, Jemima Kang, Nick Haslam, Chris Groot, Alsa Wu, Luc Raszewski, Yulia Otmakhova: Automatic Evaluation of Mental Health Stigma in Online Communication arxiv.org/abs/2610.02775 arxiv.org/pdf/2610.02775 arxiv.org/html/2610.02775

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Ding Wu, Ye Zhang, Haoyu Wang, Tianci Liu: Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing arxiv.org/abs/2610.02772 arxiv.org/pdf/2610.02772 arxiv.org/html/2610.02772

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Hy Nguyen, Nabi Rezvani, Robin Vujanic: AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving Migration arxiv.org/abs/2610.02770 arxiv.org/pdf/2610.02770 arxiv.org/html/2610.02770

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Jingyu Liu, Zhiwen Wang, Yuxin Jing, Huanyu Zhou, Yong Liu: When History Fails to Become Experience: Action Calibration in Language Agents arxiv.org/abs/2610.02769 arxiv.org/pdf/2610.02769 arxiv.org/html/2610.02769

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Zeeshan Memon, Yiqi Su, Kai Shu, Naren Ramakrishnan, Liang Zhao: EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models arxiv.org/abs/2610.02744 arxiv.org/pdf/2610.02744 arxiv.org/html/2610.02744

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Wen-Zhi Li, Yue Gong, Konstantinos Kanellis, Balakrishnan Murali Narayanaswamy: Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL arxiv.org/abs/2610.02739 arxiv.org/pdf/2610.02739 arxiv.org/html/2610.02739

000

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 18h

Minji Park, Seunghyun Yoon, Hyuk Lim: TPBench: A Turning-Point Benchmark for Dialogue Compression arxiv.org/abs/2610.02736 arxiv.org/pdf/2610.02736 arxiv.org/html/2610.02736

000