Xiaofei Wen

I am a first year PhD Student in the Department of Computer Science at the University of California, Davis, working on Natural Lanuage Processing and advised by Prof. Muhao Chen.

I am driven by the aspiration to develop intelligent systems capable of seamless interactions with humans.

Email: xfwe[at]ucdavis[dot]edu

CV  /  Google Scholar  /  Twitter  /  Linkedin  /  Github

profile photo
News
  • [Jul, 2025] New! Our new study on multi-turn red teaming for Code LLMs is available at Preprint.
  • [May, 2025] New! Our new study on cross-modality competency in MLLMs is available at Preprint.
  • [May, 2025] New! Our Guardrail paper is accepted by ACL 2025. Check out ThinkGuard!
  • [Sep, 2024] New! Our Contradictory Dialogue paper is accepted by EMNLP 2024!
  • [May, 2024] New! One paper is accepted by ACL 2024!
Publications

I'm interested in LLM Reasoning, AI safety and Multimodal model task perception problems. Representative papers are highlighted.

REDCODER: Automated Multi-Turn Red Teaming for Code LLMs
Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung, Hadi Askari, Wenxuan Zhou, Zhe Zhao, Muhao Chen
Preprint, 2025
arxiv / code
Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
Rui Cai, Bangzheng Li, Xiaofei Wen, Muhao Chen, Zhe Zhao
Preprint, 2025
arxiv / code
ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails
Xiaofei Wen, Wenxuan Zhou, Wenjie Jacky Mo, Muhao Chen
Findings of the Conference of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL-Findings), 2025
arxiv / code / model
MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design
Jingyuan Qi, Zian Jia, Minqian Liu, Wangzhi Zhan, Junkai Zhang, Xiaofei Wen, Jingru Gan, Jianpeng Chen, Qin Liu, Mingyu Derek Ma, Bangzheng Li, Haohui Wang, Adithya Kulkarni, Muhao Chen, Dawei Zhou, Ling Li, Wei Wang, Lifu Huang
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations), 2025
paper / demo
Red Teaming Language Models for Processing Contradictory Dialogues
Xiaofei Wen, Bangzheng Li, Tenghao Huang, Muhao Chen
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
paper / code
Personalized Topic Selection Model for Topic-Grounded Dialogue
Shixuan Fan, Wei Wei, Xiaofei Wen, Xianling Mao, Jixiong Chen, Danyang Chen
Findings of the Conference of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL-Findings), 2024
paper
Sequential Topic Selection Model with Latent Variable for Topic-Grounded
Xiaofei Wen, Wei Wei, Xianling Mao
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2022
paper
Education

University of California, Davis, Ph.D. in Computer Science 2024-Present

Huazhong University of Science and Technology, M.S. in Computer Science 2021-2024

Dalian University of Technology, B.Eng in Software Engineering 2017-2021

Service
  • Conference Reviewer: NAACL, ACL, EMNLP since 2023
  • Vice President: Model United Nations of DUT, 2018–2019
    		•
    Miscellaneous

    I'm a big fan of gangster films — it all started with The Godfather trilogy, which got me hooked on the genre, especially drawn to the performances of Al Pacino and Robert De Niro. I also love Breaking Bad and Better Call Saul. And for the record, I'm proudly ShinRan/新蘭派


    Website source code from Jon Barron.