About Me
I am a second-year Ph.D. student in the UCI-NLP at the University of California, Irvine, where I am fortunate to be advised by Sameer Singh. My current research interests are centered around natural language reasoning, understanding and evaluating NLP systems.
Previously, I got my M.S. in Computer Science from ETH Zurich, advised by Mrinmaya Sachan. Before that I obtained a B.S. in Theoretical and Applied Mechanics from Peking University, where I worked with Yizhou Wang. I also spent wonderful a half year worked as a research intern at EPFL working with Antoine Bosselut prior to joining UCI.
Email: [firstname].fei@uci.edu
Recent News
- 2024 - Check our new preprint on inference-time alignment! [website]
- 2023 - Paper accepted to EMNLP 2023 “Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models”! [pdf] [code]
- 2023 - Joined the UCI-NLP.
- 2023 - Paper accepted to ACL 2023 “Mitigating Label Biases for In-context Learning” [pdf] [code]
- 2022 - Paper accepted to EMNLP 2022: “Beyond prompting: Making pre-trained language models better zero-shot learners by clustering representations” [pdf] [code]
- 2022 - Started research internship at EPFL supervised by Antoine Bosselut.
- 2022 - Graduated with a M.S. in Computer Science with distinction from ETH Zurich.
Publications and Preprints
Nudging: Inference-time Alignment via Model Collaboration
Yu Fei, Yasaman Razeghi, Sameer Singh
Preprint
[paper] [code] [website] [demo]
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan
EMNLP 2023
[paper] [code]
Mitigating Label Biases for In-context Learning
Yu Fei, Yifan Hou, Zeming Chen, Antoine Bosselut
ACL 2023
[paper] [code]
Beyond prompting: Making pre-trained language models better zero-shot learners by clustering representations
Yu Fei, Ping Nie, Zhao Meng, Roger Wattenhofer, Mrinmaya Sachan
EMNLP 2022
[paper] [code]
Align, attend and locate: Chest x-ray diagnosis via contrast induced attention network with limited supervision
Jingyu Liu, Gangming Zhao, Yu Fei, Ming Zhang, Yizhou Wang, Yizhou Yu
ICCV 2019
[paper]