Weiyan Shi

Recent Preprints

• SPADE: Self-Play in Adaptive Synthetic Executable Environments

  Bo Liu*, Simon Yu*, Yiding Jiang, Ao Qu, Andrew Zhao, Zichen Liu, Junsu Kim, Zijian Zhou, Seungone Kim, Tongzheng Ren, Mickel Liu, Hanfei Yu, Zhaorun Chen, Weiyan Shi, Paul Pu Liang, Luke Zettlemoyer, Yejin Choi, Natasha Jaques

  (*equal contribution)

  arXiv, 2026 [pdf] [code] [project page]

Publications [Google Scholar] [Show Selected] [Show All]

• Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces

  Simon Yu*, Derek Chong*, Ananjan Nandi*, Dilara Soylu, Jiuding Sun, Christopher D. Manning, Weiyan Shi

  (*equal contribution)

  NeurIPS, 2026 [pdf] [homepage] [code (2.4k ⭐)] [docs]

• Agents' Last Exam

  Yiyou Sun et al. (multi-institution collaboration led by Berkeley RDI)

  NeurIPS, 2026 [pdf] [code] [blog]

• Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

  Jingheng Ye*, Huiqi Zou*, Simon Yu, Weiyan Shi

  (*equal contribution)

  NeurIPS, 2026 [pdf]

  Best Paper, DL4C@ICML 2026

• The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

  Jiachen Zhao, Zhengxuan Wu, Aryaman Arora, Yiyou Sun, David Bau, Weiyan Shi

  NeurIPS, 2026 [pdf]

• One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

  Simon Yu, Nicholas Tomlin, Marwa Abdulhai, Ximing Lu, Derek Chong, Abe Hou, Dilara Soylu, Sergey Levine, Christopher D. Manning, Weiyan Shi

  EMNLP, 2026 [pdf]

• Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation

  Mingqi Gao, Anthony Sicilia, Weiyan Shi

  EMNLP, 2026 [pdf]

• Can Aha Moments Be Fake? Identifying True and Decorative Thinking Steps in Chain-of-Thought

  Jiachen Zhao, Yiyou Sun, Weiyan Shi†, Dawn Song†

  (†equal advising)

  EMNLP Findings, 2026 [pdf]

  Selected Media Coverage

  [Quanta Magazine]

• Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-Playing LLM Training

  Qihui Fan, Min Ge, Chenyan Jia, Weiyan Shi

  COLM, 2026 [pdf]

• Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

  Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Bo Li, Dawn Song, Xue Lin, Weiyan Shi

  ICML, 2026 [pdf] [project page]

• Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

  Jiayi Zhang*, Simon Yu*, Derek Chong*, Anthony Sicilia, Michael R. Tomz, Christopher D. Manning, Weiyan Shi

  (*equal contribution)

  ICML, 2026 [pdf] [X thread] [blog] [code] [colab] [gallery] [homepage]

  Selected Media Coverage

  [Forbes] [TLDR AI] [Yahoo News] [VentureBeat] [Neuron Daily] [AI in Education Daily Podcast] [AI Papers Podcast Daily] [Analytics Vidhya]

• Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effects

  Isabel O. Gallegos, Chen Shani, Weiyan Shi, Federico Bianchi, Izzy Gainsburg, Dan Jurafsky, Robb Willer

  PNAS Nexus, 2026 [pdf]

• PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction

  Simon Yu, Gang Li, Weiyan Shi†, Peng Qi†

  (†equal advising)

  ICLR, 2026 [pdf]

• SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models

  Hamza Tahboub, Weiyan Shi, Gang Hua, Huaizu Jiang

  TMLR, 2026 [pdf]

• GEM: A Gym for Agentic LLMs

  Zichen Liu, Anya Sims, Keyu Duan, Changyu Chen, Simon Yu, Xiangxin Zhou, Haotian Xu, Shaopan Xiong, Bo Liu, Chenmien Tan, Chuen Yang Beh, Weixun Wang, Hao Zhu, Weiyan Shi, Diyi Yang, Michael Shieh, Yee Whye Teh, Wee Sun Lee, Min Lin

  ICLR, 2026 [pdf] [code]

  Outstanding Paper, SEA@NeurIPS 2025

• SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

  Bo Liu*, Simon Yu*, Zichen Liu*, Leon Guertler*, Penghui Qi, Daniel Balcells, Mickel Liu, Cheston Tan, Weiyan Shi, Min Lin, Wee Sun Lee, Natasha Jaques

  (*equal contribution)

  ICLR, 2026 [pdf]

• LLMs Encode Harmfulness and Refusal Separately

  Jiachen Zhao, Jing Huang, Zhengxuan Wu, David Bau, Weiyan Shi

  NeurIPS, 2025 [pdf] [code] [project page] [blog]

• Distilling an End-to-End Voice Assistant Without Instruction Training Data

  William Held, Yanzhe Zhang, Minzhi Li, Weiyan Shi, Michael J. Ryan, Diyi Yang

  ACL, 2025 [pdf]

• NewsInterview: A Dataset and a Playground to Evaluate LLMs' Grounding Gap via Informational Interviews

  Alexander Spangher, Michael Lu, Sriya Kalyan, Hyundong Justin Cho, Tenghao Huang, Weiyan Shi, Jonathan May

  ACL, 2025 [pdf]

• Proactive Conversational Agents with Inner Thoughts

  Xingyu Bruce Liu, Shitao Fang, Weiyan Shi, Chien-Sheng Wu, Takeo Igarashi, Xiang Anthony Chen

  CHI, 2025 [pdf]

• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

  Yijia Shao, Tianshi Li, Weiyan Shi, Yanchen Liu, Diyi Yang

  NeurIPS D&B, 2024 [pdf]

• Zero-Shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval

  Kazuaki Furumai, Roberto Legaspi, Julio Vizcarra, Yudai Yamazaki, Yasutaka Nishimura, Sina J. Semnani, Kazushi Ikeda, Weiyan Shi, Monica S. Lam

  EMNLP Findings, 2024 [pdf]

• CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies

  Weiyan Shi, Ryan Li, Yutong Zhang, Caleb Ziems, Sunny Yu, Raya Horesh, Rogério Abreu de Paula, Diyi Yang

  EMNLP Findings, 2024 [pdf]

• Dialoging Resonance in Human-Chatbot Conversation: How Users Perceive and Reciprocate Recommendation Chatbot's Self-Disclosure Strategy

  Kai-Hui Liang, Weiyan Shi, Yoo Jung Oh, Hao-Chuan Wang, Jingwen Zhang, Zhou Yu

  CSCW, 2024 [pdf]

• A Safe Harbor for AI Evaluation and Red Teaming

  Shayne Longpre, Sayash Kapoor, Kevin Klyman, Ashwin Ramaswami, Rishi Bommasani, Borhane Blili-Hamelin, Yangsibo Huang, Aviya Skowron, Zheng-Xin Yong, Suhas Kotha, Yi Zeng, Weiyan Shi, Xianjun Yang, Reid Southen, Alexander Robey, Patrick Chao, Diyi Yang, Ruoxi Jia, Daniel Kang, Sandy Pentland, Arvind Narayanan, Percy Liang, Peter Henderson

  ICML Position Track, 2024 [pdf]

• Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future

  Minzhi Li, Weiyan Shi, Caleb Ziems, Diyi Yang

  ACL Findings, 2024 [pdf]

• How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

  Yi Zeng*, Hongpeng Lin*, Jingwen Zhang, Diyi Yang, Ruoxi Jia†, Weiyan Shi†

  (*equal contribution, †equal advising)

  ACL, 2024 [pdf] [project page] [code & data]

  Best Social Impact Paper

• The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

  Myeongseob Ko, Feiyang Kang, Weiyan Shi, Ming Jin, Zhou Yu, Ruoxi Jia

  CVPR, 2024 [pdf]

• The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation

  Rongwu Xu, Brian S. Lin, Shujian Yang, Tianqi Zhang, Weiyan Shi†, Tianwei Zhang, Zhixuan Fang, Wei Xu, Han Qiu†

  (†equal advising)

  ACL, 2024 [pdf] [project page] [code & data]

  Outstanding Paper

• AutoReply: Detecting Nonsense in Dialogue with Discriminative Replies

  Weiyan Shi, Emily Dinan, Adi Renduchintala, Daniel Fried, Athul Jacob, Zhou Yu, Mike Lewis

  EMNLP Findings, 2023 [pdf]

• Controllable Mixed-Initiative Dialogue Generation through Prompting

  Maximillian Chen, Xiao Yu, Weiyan Shi, Urvi Awasthi, Zhou Yu

  ACL, 2023 [pdf]

• Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning

  Meta Fundamental AI Research Diplomacy Team (FAIR), Anton Bakhtin*, Noam Brown*, Emily Dinan*, Gabriele Farina, Colin Flaherty*, Daniel Fried, Andrew Goff, Jonathan Gray*, Hengyuan Hu*, Athul Paul Jacob*, Mojtaba Komeili, Karthik Konath, Minae Kwon, Adam Lerer*, Mike Lewis*, Alexander H. Miller*, Sasha Mitts, Adithya Renduchintala*, Stephen Roller, Dirk Rowe, Weiyan Shi*, Joe Spisak, Alexander Wei, David Wu*, Hugh Zhang*, Markus Zijlstra

  (*core research team member; authors listed alphabetically)

  Science, 2022 [pdf] [code]

  Selected Media Coverage

  [New York Times (front page)] [The Washington Post] [The Economist] [MIT Technology Review] [Forbes] [Meta AI blog post] [Commentary in Science News]

• When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels

  Weiyan Shi, Emily Dinan, Kurt Shuster, Jason Weston, Jing Xu

  NAACL, 2024 [pdf]

• Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks

  Kushal Chawla*, Weiyan Shi*, Jingwen Zhang, Gale Lucas, Zhou Yu, Jonathan Gratch

  (*equal contribution)

  EACL, 2023 [pdf]

• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models

  Weiyan Shi, Ryan Shea, Si Chen, Chiyuan Zhang, Ruoxi Jia, Zhou Yu

  EMNLP, 2022 [pdf]

• Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue

  Maximillian Chen, Weiyan Shi, Feifan Yan, Ryan Hou, Jingwen Zhang, Saurav Sahay, Zhou Yu

  AACL, 2022 [pdf]

• Selective Differential Privacy for Language Modeling

  Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, Zhou Yu

  NAACL, 2022 [pdf] [code & data] [talk]

• PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation

  Jing Gu, Qingyang Wu, Chongruo Wu, Weiyan Shi, Zhou Yu

  ACL, 2021 [pdf]

• LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing

  Yu Li, Josh Arnold, Feifan Yan, Weiyan Shi, Zhou Yu

  ACL Demo, 2021 [pdf]

• Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration

  Weiyan Shi, Yu Li, Saurav Sahay, Zhou Yu

  EMNLP Findings, 2021 [pdf]

• Understanding User Resistance Strategies in Persuasive Conversations

  Youzhi Tian, Weiyan Shi, Chen Li, Zhou Yu

  EMNLP Findings, 2020 [pdf]

• INSPIRED: Toward Sociable Recommendation Dialog Systems

  Shirley Anugrah Hayati, Dongyeop Kang, Qingxiaoyang Zhu, Weiyan Shi, Zhou Yu

  EMNLP, 2020 [pdf]

• Effects of Persuasive Dialogues: Testing Bot Identities and Inquiry Strategies

  Weiyan Shi, Xuewei Wang, Yoo Jung Oh, Jingwen Zhang, Saurav Sahay, Zhou Yu

  CHI, 2020 [pdf]

• End-to-End Trainable Non-Collaborative Dialog System

  Yu Li, Kun Qian, Weiyan Shi, Zhou Yu

  AAAI, 2020 [pdf]

• Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good

  Xuewei Wang*, Weiyan Shi*, Richard Kim, Yoo Jung Oh, Sijia Yang, Jingwen Zhang, Zhou Yu

  (*equal contribution)

  ACL, 2019 [pdf] [code & data] [talk]

  Best Paper Nomination

• Unsupervised Dialog Structure Learning

  Weiyan Shi, Tiancheng Zhao, Zhou Yu

  NAACL, 2019 [pdf]

• How to Build User Simulators to Train RL-based Dialog Systems

  Weiyan Shi*, Kun Qian*, Xuewei Wang, Zhou Yu

  (*equal contribution)

  EMNLP, 2019 [pdf]

• Sentiment Adaptive End-to-End Dialog Systems

  Weiyan Shi, Zhou Yu

  ACL, 2018 [pdf]