Fei Wang


Los Angeles, CA

I am a Ph.D. candidate in computer science at University of Southern California. I am grateful to be co-advised by Muhao Chen and Aram Galstyan, and I am fortunate to work closely with Kai-Wei Chang. My research is supported by the Amazon ML Fellowship and the Annenberg Fellowship. Previously, I was a research intern at Amazon Web Services (AWS) AI, Amazon Alexa AI, and Tencent AI Lab (Seattle).

I am broadly interested in natural language processing and machine learning. My long-term goal is to build robust, controllable, and accountable and responsible large language models. My recent work spans across (1) mitigating knowledge conflicts and spurious correlations, (2) guiding text generation using constraints, and (3) enhancing model privacy and security against information leakage and backdoor attacks.


Oct 2, 2023 I will give a tutorial at EMNLP 2024 on ‚ÄúEnhancing LLM Capabilities Beyond Scaling Up‚ÄĚ with Wenpeng Yin, Muhao Chen, Rui Zhang, Ben Zhou, and Dan Roth.
Jul 28, 2023 I’ve been selected to be an Amazon ML Fellow!
May 2, 2023 Two papers on debiasing NLU and factuality in summarization are accepted by ACL 2023.
Nov 29, 2022 I’m officially a PhD candidate!
Oct 6, 2022 Our papers on salience-guided abstractive summarization and spurious correlations in entity typing are accepted by EMNLP 2022.

Selected Publications

  1. EMNLP
    Fei Wang, Wenjie Mo, Yiwei Wang, Wenxuan Zhou, and Muhao Chen
    In Findings of EMNLP 2023
  2. ACL
    Fei Wang*, James Y. Huang*, Tianyi Yan, Wenxuan Zhou, and Muhao Chen
    In Findings of ACL 2023
  3. EMNLP
    Fei Wang*, Kaiqiang Song*, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, and Dong Yu
    In Proceedings of EMNLP 2022
  4. NAACL
    Fei Wang, Zhewei Xu, Pedro Szekely, and Muhao Chen
    In Proceedings of NAACL 2022