Xuhui Zhou

Last update: March 27, 2025

Contact

Address:
4902 Forbes Ave, Gates Hillman Complex, Pittsburgh, PA

Homepage: https://xuhuiz.com/
Email: xuhuiz@cs.cmu.edu
Tel: 206-306-5850

Research

Socially intelligent AI agents. Specifically, I am interested in facilitating pro-social agents that interact cooperatively and safely, align with human values, and contribute positively to individual and societal well-being.

Education

Carnegie Mellon University, Pittsburgh, PA (Aug 2022)
PhD in Computer Science (Language Technologies)
Advisor: Maarten Sap

University of Washington, Seattle, WA (Sep 2019 - Jun 2021)
M.Sc in Computational Linguistics
Advisor: Noah Smith

Nanjing University, Nanjing, China (Sep 2015 - Jun 2019)
B.Sc in Statistics, Department of Mathematics
Advisor: Shujian Huang

University of California Berkeley, Berkeley, CA (visiting student) (Aug 2017 - May 2018)

Industry Experience

Allen Institute for Artificial Intelligence
Research Intern (May 2024 - Aug 2024)

Machine Intelligence @ Apple
Research Intern (Mar 2021 - Sep 2021)

Recent Preprints

(*Equal contribution)

  1. TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
    Frank F. Xu, Yufan Song, Boxuan Li, Yuxuan Tang, Kritanjali Jain, Mengxue Bao, Zora Z. Wang, Xuhui Zhou, Zhitong Guo, Murong Cao, Mingyang Yang, Hao Yang Lu, Amaad Martin, Zhe Su, Leander Maben, Raj Mehta, Wayne Chi, Lawrence Jang, Yiqing Xie, Shuyan Zhou, Graham Neubig

  2. Interactive Agents to Overcome Ambiguity in Software Engineering
    Sanidhya Vijayvargiya, Xuhui Zhou, Akhila Yerukola, Maarten Sap, Graham Neubig

  3. Minion: A Technology Probe for Resolving Value Conflicts through Expert-Driven and User-Driven Strategies in AI Companion Applications
    Xianzhe Fan, Qing Xiao, Xuhui Zhou, Yuran Su, Zhicong Lu, Maarten Sap, Hong Shen

  4. BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
    Wenkai Li, Jiarui Liu, Andy Liu, Xuhui Zhou, Mona Diab, Maarten Sap

  5. HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
    Xuhui Zhou, Hyunwoo Kim*, Faeze Brahman*, Liwei Jiang, Hao Zhu, Ximing Lu, Frank Xu, Bill Yuchen Lin, Yejin Choi, Niloofar Mireshghallah, Ronan Le Bras, Maarten Sap
    Website

  6. On the Resilience of Multi-Agent Systems with Malicious Agents
    Jen-tse Huang, Jiaxu Zhou, Tailin Jin, Xuhui Zhou, Zixi Chen, Wenxuan Wang, Youliang Yuan, Maarten Sap, Michael R. Lyu

Publications

(*Equal contribution)

  1. Bridging the Data Provenance Gap Across Text, Speech and Video
    Shayne Longpre, Nikhil Singh, Manuel Cherep, Kushagra Tiwary, Joanna Materzynska, William Brannon, Robert Mahari, Naana Obeng-Marnu, Manan Dey, Mohammed Hamdy, Nayan Saxena,…, Vivek Sharma, Xuhui Zhou, Caiming Xiong, Luis Villa, Stella Biderman, Alex Pentland, Sara Hooker, Jad Kabbara
    ICLR 2025

  2. AutoPresent: Designing Structured Visuals from Scratch
    Jiaxin Ge, Zora Zhiruo Wang, Xuhui Zhou, Yi-Hao Peng, Sanjay Subramanian, Qinyue Tan, Maarten Sap, Alane Suhr, Daniel Fried, Graham Neubig, Trevor Darrell
    CVPR 2025

  3. User-Driven Value Alignment: Understanding Users’ Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions
    Xianzhe Fan, Qing Xiao, Xuhui Zhou, Jiaxin Pei, Maarten Sap, Zhicong Lu, Hong Shen
    CHI 2025

  4. SOTOPIA-S4: A User-Friendly System for Flexible, Customizable, and Large-Scale Social Simulation
    Xuhui Zhou, Zhe Su, Sophie Feng, Jiaxu Zhou, Jen-tse Huang, Svitlana Volkova, Tongshuang Sherry Wu, Anita Woolley, Hao Zhu, Maarten Sap
    NAACL System Demonstrations 2025, Website

  5. AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents
    Zhe Su, Xuhui Zhou, Sanketh Rangreji, Anubha Kabra, Julia Mendelsohn, Faeze Brahman, Maarten Sap
    NAACL 2025

  6. Consent in crisis: The rapid decline of the ai data commons
    Shayne Longpre, Robert Mahari, Ariel Lee, …, Xuhui Zhou, Yizhi Li, Caiming Xiong, Luis Villa, Stella Biderman, Hanlin Li, Daphne Ippolito, Sara Hooker, Jad Kabbara, Sandy Pentland
    NeurIPS Datasets and Benchmarks 2024

  7. PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
    Devansh Jain, Priyanshu Kumar, Samuel Gehman, Xuhui Zhou, Thomas Hartvigsen, Maarten Sap
    COLM 2024

  8. Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
    Xuhui Zhou, Zhe Su, Tiwalayo Eisape, Hyunwoo Kim, Maarten Sap
    EMNLP 2024, Website

  9. SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
    Xuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang, Zhengyang Qi, Haofei Yu, Louis-Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig, Maarten Sap
    ICLR 2024, Spotlight, Website

  10. WebArena: A Realistic Web Environment for Building Autonomous Agents
    Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Yonatan Bisk, Daniel Fried, Uri Alon, Graham Neubig
    ICLR 2024

  11. Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
    Niloofar Mireshghallah, Hyunwoo Kim, Xuhui Zhou, Yulia Tsvetkov, Maarten Sap, Reza Shokri, Yejin Choi
    ICLR 2024, Spotlight

  12. FANTOM: A Benchmark for Analyzing Theory of Mind in Conversations
    Hyunwoo Kim, Melanie Sclar, Xuhui Zhou, Ronan Le Bras, Gunhee Kim, Yejin Choi, Maarten Sap
    EMNLP 2023

  13. Don’t Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting
    Akhila Yerukola, Xuhui Zhou, Maarten Sap
    EMNLP 2023

  14. Learning to translate by learning to communicate
    C.M. Downey, Xuhui Zhou, Leo Z. Liu, Shane Steinert-Threlkeld
    EMNLP MRL 2023

  15. Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models
    Natalie Shapira, Mosh Levy, Hossein Seyed Alavi, Xuhui Zhou, Yejin Choi, Yoav Goldberg, Maarten Sap, and Vered Shwartz
    EACL 2023

  16. Cobra frames: Contextual Reasoning about Effects and Harms of Offensive Statements
    Xuhui Zhou, Hao Zhu, Akhila Yerukola, Thomas Davidson, Jena D. Hwang, Swabha Swayamdipta, Maarten Sap
    Findings of ACL 2023

  17. Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection
    Maarten Sap, Swabha Swayamdipta, Laura Vianna, Xuhui Zhou, Yejin Choi, Noah A. Smith
    NAACL 2022

  18. Emergent Communication Fine-tuning (EC-FT) for Pretrained Language Models
    Shane Steinert-Threlkeld, Xuhui Zhou, Zeyu Liu, C. M. Downey
    ICLR EmeCom 2022, Runner-up Best Paper

  19. Extracting and Inferring Personal Attributes from Dialogue
    Zhilin Wang, Xuhui Zhou, Rik Koncel-Kedziorski, Alex Marin, Fei Xia
    ACL ConvAI, 2022

  20. Challenges in Automated Debiasing for Toxic Language Detection
    Xuhui Zhou, Maarten Sap, Swabha Swayamdipta, Noah A.Smith, Yejin Choi
    EACL, 2021

  21. Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets
    Chuanrong Li, Lin Shengshuo, Zeyu Liu, Xinyi Wu, Xuhui Zhou, Shane Steinert-Threlkeld
    *EMNLP BlackboxNLP, 2020

  22. Multilevel Text Alignment with Cross-Document Attention
    Xuhui Zhou, Nikolaos Pappas, Noah A. Smith
    EMNLP, 2020

  23. Evaluating Commonsense in Pre-trained Language Models
    Xuhui Zhou, Yue Zhang, Leyang Cui, Dandan Huang
    AAAI, 2020

  24. RPD: A Distance Function Between Word Embeddings
    Xuhui Zhou, Zaixiang Zheng, Shujian Huang
    ACL Student Research Workshop, 2020

Invited Talks

Ethics and Safety in LLMs

Awards & Media Coverage

Service