Fei Wang

profile.jpg

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. I am also fortunate to work closely with Kai-Wei Chang. My research is supported by the Amazon ML PhD Fellowship and the Annenberg PhD Fellowship. Previously, I was a research intern at AWS AI Labs, Amazon Alexa AI, and Tencent AI Lab (Seattle).

My research interests lie in natural language processing and machine learning. My recent work focuses on responsible and trustworthy LLMs, including (1) robustness and faithfulness, (2) safety and security, and (3) controllable generation.

News

Nov 15, 2024 Tutorial at EMNLP 2024 on “Enhancing LLM Capabilities Beyond Scaling Up.”
Jun 16, 2024 Six papers accepted by NAACL 2024. See you in Mexico City!
Apr 30, 2024 Invited talk at the 3rd Annual Symposium of USC-Amazon Center.

Selected Publications

  1. preprint
    From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
    Fei Wang, Chao Shang , Sarthak Jain , Shuai Wang , Qiang Ning , Bonan Min , Vittorio Castelli , Yassine Benajiba , and Dan Roth
    2024
  2. EMNLP
    A Causal View of Entity Bias in (Large) Language Models
    Fei Wang, Wenjie Mo , Yiwei Wang , Wenxuan Zhou , and Muhao Chen
    In Findings of EMNLP , 2023
  3. ACL
    Robust Natural Language Understanding with Residual Attention Debiasing
    Fei Wang*, James Y. Huang* , Tianyi Yan , Wenxuan Zhou , and Muhao Chen
    In Findings of ACL , 2023
  4. EMNLP
    Salience Allocation as Guidance for Abstractive Summarization
    Fei Wang*, Kaiqiang Song* , Hongming Zhang , Lifeng Jin , Sangwoo Cho , Wenlin Yao , Xiaoyang Wang , Muhao Chen , and Dong Yu
    In Proceedings of EMNLP , 2022
  5. NAACL
    Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning
    Fei Wang, Zhewei Xu , Pedro Szekely , and Muhao Chen
    In Proceedings of NAACL , 2022