Publications

Weihao Xuan*, Qingcheng Zeng*, Jiarui Liu*, Rui Yang*, Yunze Xiao, Yinxi Li, Zeqi Zhou, Weiwei Sun, Heli Qi, Leyang Cui, Tianhao Ma, Hanqun Cao, Junjue Wang, Tianyu Liu, Weihua Du, Yueqi Song, Jiayi Geng, Matthew Yu Heng Wong, Rob Voigt, Chuan Hong, Xiang Yue, Jen-Tse Huang, Xuhai Xu, Yifan Peng, Pheng Ann Heng, Yiming Yang, Bernhard Schölkopf, Zhijing Jin, Nan Liu, Naoto Yokoya, Mona Diab (2026). Learning from Use: Test-Time Learning in Large Language Models and Agents. Preprint 2026.

Rui Yang, Weihao Xuan, Yi Lin, Zhuhan Bao, Jonathan Chong Kai Liew, Matthew Yu Heng Wong, Nicolás Lescano, Nikita R Paripati, Emily Ling-Lin Pai, Jiarui Liu, Heli Qi, Heng-Jui Chang, Benny Kai Guo Loo, Huitao Li, Kunyu Yu, Yufan Wang, Chuan Hong, Shijian Lu, Douglas Teodoro, Naoto Yokoya, Ross Koppel, Mona Diab, Hua Xu, David W Bates, Nan Liu, Yifan Peng (2026). Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases. Preprint 2026.

Yueqi Song, Lintang Sutawika, Jiarui Liu, Lindia Tjuatja, Jiayi Geng, Yunze Xiao, Daniel Lee, Aditya Bharat Soni, Vincent Lo, Xiang Yue, Graham Neubig (2026). PACE: A Proxy for Agentic Capability Evaluation. Preprint 2026.

Jiarui Liu, Terry Jingchen Zhang, Ryan Faulkner, Xuanqiang Angelo Huang, Vilém Zouhar, Dominik Glandorf, Isabel Dahlgren, Rishit Dagli, Yuen Chen, Felix Leeb, Van Q Truong, Punya Syon Pandey, Yves Bicker, Suvajit Majumder, Wenyuan Jiang, Zeju Qiu, Sankalan Pal Chowdhury, Mrinmaya Sachan, Bernhard Schölkopf, Mona Diab, Zhijing Jin (2026). PaperMentor: A human-centered multi-agent writing tutor for AI research papers in Overleaf. ACL 2026 Demo.

ACL Anthology Code Demo

Xuhui Zhou, Weiwei Sun, Weihua Du, Jiarui Liu, Haojia Sun, Qianou Ma, Tongshuang Wu, Yiming Yang, Maarten Sap (2026). OdysSim: Building Foundation Models for Human Behavior Simulation. Preprint 2026.

Lechen Zhang, Jiarui Liu, Tal August (2026). Re-Centering Humans in LLM Personalization. Preprint 2026.

Sheng Jin, Minghao Liu, Yunze Xiao, Zeqi Zhou, Heli Qi, Yifan Yao, Meishu Song, Kaijing Ma, Xuan Zhang, Sicong Jiang, Yizhe Li, Ningshan Ma, Jie Wei, Ziniu Li, Minglai Yang, Bangya Liu, Yiming Liang, Xiao Fang, Qingcheng Zeng, Jiarui Liu, Rui Yang, Shen Yan, Wenhao Huang, Jiaheng Liu, Zihan Wang, Weihao Xuan, Ge Zhang (2026). Knowledge Index of Noah's Ark. Preprint 2026.

Chunyuan Deng, Yizhe Zhang, Rui-Jie Zhu, Yuanyuan Xu, Jiarui Liu, TS Ng, Hanjie Chen (2026). LT2: Linear-Time Looped Transformers. Preprint 2026.

Weiwei Sun, Xuhui Zhou, Jiarui Liu, Weihua Du, Haojia Sun, Yiqing Xie, Qianou Ma, Sihao Chen, Mengting Wan, Longqi Yang, Pei Zhou, Sherry Wu, Sean Welleck, Graham Neubig, Yiming Yang, Maarten Sap (2026). Reinforcing Human Behavior Simulation via Verbal Feedback. Preprint 2026.

Jiarui Liu, Lechen Zhang, Yongjin Yang, Yinghui He, Yingheng Wang, Weihao Xuan, Zhijing Jin, Mona Diab (2026). MixSD: Mixed Contextual Self-Distillation for Knowledge Injection. Preprint 2026.

Yongjin Yang, Jiarui Liu, Yinghui He, Lezhen Zhang, Bernhard Schölkopf, Zhijing Jin (2026). Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR. Best Paper Award at ICML 2026 RLxF Workshop.

Yinghui He, Simran Kaur, Adithya Bhaskar, Yongjin Yang, Jiarui Liu, Narutatsu Ri, Liam Fowl, Abhishek Panigrahi, Danqi Chen, Sanjeev Arora (2026). Self-distillation zero: Self-revision turns binary rewards into dense supervision. Best Paper Award at ICML 2026 RLxF Workshop.

Florent Draye, Abir Harrasse, Vedant Palit, Tung-Yu Wu, Jiarui Liu, Punya Syon Pandey, Roderick Wu, Terry Jingchen Zhang, Zhijing Jin, Bernhard Schölkopf (2026). CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs. Preprint 2026.

Xuhui Zhou, Weiwei Sun, Qianou Ma, Yiqing Xie, Jiarui Liu, Weihua Du, Sean Welleck, Yiming Yang, Graham Neubig, Sherry Tongshuang Wu, Maarten Sap (2026). Mind the sim2real gap in user simulation for agentic tasks. Preprint 2026.

Yongjin Yang, Yinghui He, Jiarui Liu, Zhijing Jin (2026). Making Complex Reasoning Student-Friendly: A Hybrid LLM-to-SLM Distillation Framework. Preprint 2026.

Jiarui Liu, Kaustubh Dhole, Yingheng Wang, Haoyang Wen, Sarah Zhang, Haitao Mao, Gaotang Li, Neeraj Varshney, Jingguo Liu, Xiaoman Pan (2025). Stabilizing Reinforcement Learning for Honesty Alignment in Language Models on Deductive Reasoning. AAAI 2026 Bridge LMReasoning Workshop, AAAI 2026 MATH4AI Workshop.

Jiarui Liu*, Jivitesh Jain*, Mona Diab, Nishant Subramani (2025). LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Use. COLM 2025 Interplay Workshop.

Sawal Acharya, Terry Jingchen Zhang, Andrew Kim, Anahita Haghighat, Sun Xianlin, Pepijn Cobben, Rahul Babu Shrestha, Maximilian Mordig, Jacob T. Emmerson, Furkan Danisman, Yuen Chen, Clijo Jose, Andrei Ioan Muresanu, Justin Cui, Jiarui Liu, Yahang Qi, Punya Syon Pandey, Yinya Huang, Bernhard Schölkopf, Mrinmaya Sachan (2025). CauSciBench: A Comprehensive Benchmark on End-to-End Causal Inference for Scientific Research. ICML 2026.

Jiarui Liu, Weihao Xuan, Zhijing Jin, Mona Diab (2025). Taming Object Hallucinations with Verified Atomic Confidence Estimation. EACL 2026.

Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin (2025). CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures. EACL 2026.

Jiarui Liu, Yueqi Song*, Yunze Xiao*, Mingqian Zheng*, Lindia Tjuatja, Jana Schaich Borg, Mona Diab, Maarten Sap (2025). Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics. EMNLP 2025 Main.

Yunze Xiao*, Lynnette Hui Xian Ng*, Jiarui Liu, Mona Diab (2025). Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design. EMNLP 2025 Main Oral.

Wenkai Li*, Jiarui Liu*, Andy Liu, Xuhui Zhou, Mona T. Diab, Maarten Sap (2025). BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data. ACL 2025 Main.

Jiarui Liu*, Iman Ouzzani*, Wenkai Li*, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, Mona Diab (2025). Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST). ACL 2025 Findings.

Neemesh Yadav*, Jiarui Liu*, Francesco Ortu, Zhijing Jin, Rada Mihalcea (2025). Uncovering and Understanding Social Media Censorship across Countries. ACL 2025 Findings.

Ruiqi He, Yushu He, Longju Bai, Jiarui Liu, Zhenjie Sun, Zenghao Tang, He Wang, Hanchen Xia, Rada Mihalcea, Naihao Deng (2025). Chumor 2.0: Towards Benchmarking Chinese Humor Understanding. ACL 2025 Findings.

Ryuki Matsuura*, Shikhar Bharadwaj*, Jiarui Liu*, Dhatchi Kunde Govindarajan (2025). EmoNews: A Spoken Dialogue System for Expressive News Conversations. SigDial 2025 Demo.

Zhijing Jin*, Max Kleiman-Weiner*, Giorgio Piatti*, Sydney Levine, Jiarui Liu, Fernando Gonzalez, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi, Bernhard Schölkopf (2024). Language Model Alignment in Multilingual Trolley Problems. ICLR 2025 and Best Paper Award at NeurIPS 2024 Pluralistic Alignment Workshop.

Zhijing Jin*, Nils Heil*, Jiarui Liu*, Shehzaad Dhuliawala*, Yahang Qi*, Bernhard Schölkopf, Rada Mihalcea, Mrinmaya Sachan (2024). Implicit Personalization in Language Models: A Systematic Study. EMNLP 2024 Findings.

Tianyue Ou, Frank F Xu, Aman Madaan, Jiarui Liu, Robert Lo, Abishek Sridhar, Sudipta Sengupta, Dan Roth, Graham Neubig, Shuyan Zhou (2024). Synatra: Turning indirect knowledge into direct demonstrations for digital agents at scale. NeurIPS 2024.

Aashiq Muhamed, Jiarui Liu, Mona Diab, Virginia Smith (2024). Inducing Elasticity in Foundation Models: Post-Training Techniques for Adaptable Inference. NeurIPS ENLSP Workshop 2024.

Ruiqi He, Yushu He, Longju Bai, Jiarui Liu, Zhenjie Sun, Zenghao Tang, He Wang, Hanchen Xia, Naihao Deng (2024). Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba. Preprint 2024.

Jiarui Liu, Wenkai Li, Zhijing Jin, Mona Diab (2024). Automatic Generation of Model and Data Cards: A Step Towards Responsible AI. NAACL 2024 Oral.

Zhijing Jin*, Yuen Chen*, Fernando Gonzalez*, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Schölkopf, Mona Diab (2024). Analyzing the Role of Semantic Representations in the Era of Large Language Models. NAACL 2024.

Zhijing Jin*, Jiarui Liu*, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona Diab, Bernhard Schölkopf (2023). Can Large Language Models Infer Causation from Correlation?. ICLR 2024.

Gaotang Li*, Jiarui Liu*, Wei Hu (2023). Bias Amplification Enhances Minority Group Performance. TMLR 2023.

Yiwen Ding*, Jiarui Liu*, Zhiheng Lyu, Kun Zhang, Bernhard Schoelkopf, Zhijing Jin, Rada Mihalcea (2023). Voices of Her: Analyzing Gender Differences in the AI Publication World. ACL 2025 NLP for Positive Impact Workshop.