Fangyuan Xu
My name in Chinese: 许方园
Pronouns: she/her
Email: fx2145[@]nyu.edu
GithubSemantic Scholar
Google Scholar
👩💻
I am a third-year Ph.D. student in Computer Science at New York University (Courant Institute), working with Eunsol Choi.
I spent the first two years of my Ph.D. at the University of Texas at Austin before transferring out. Previously, I graduated from Cornell University with a M.Eng in Computer Science and the University of Hong Kong with a B.Eng in Computer Science. I also spent some time in the industry -- I interned at Allen Institute for AI (Summer 2023) and worked as a Machine Learning Engineer at Twitter.
Research
I am interested in natural language processing and machine learning. My recent work focus on improving inference-time efficiency for long-context language models and retrieval-augmented models. I have also been working on developing careful evaluations for complex knowledge-intensive use-cases, such as long-form question answering and instruction-following for writing assistance.Publications
RefreshKV: Updating Small KV Cache During Long-form Generation, ACL 2025
Fangyuan Xu, Tanya Goyal*, Eunsol Choi*
KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions, ACL 2024 Findings
Fangyuan Xu, Kyle Lo, Luca Soldaini, Bailey Kuehl, Eunsol Choi, David Wadden
[website]
RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation, ICLR 2024
Fangyuan Xu, Weijia Shi, Eunsol Choi
[code]
Contrastive Learning to Improve Retrieval for Real-world Fact Checking, EMNLP 2024 FEVER Workshop (Oral)
Aniruddh Sriram, Fangyuan Xu, Eunsol Choi, Greg Durrett
Understanding Retrieval Augmentation for Long-Form Question Answering, COLM 2024
Hung-Ting Chen, Fangyuan Xu*, Shane Arora*, Eunsol Choi
[code]
Long-form Answers to Visual Question from Blind and Low Vision People, COLM 2024 (Spotlight)
Mina Huh, Fangyuan Xu, Yi-Hao Peng, Chongyan Chen, Hansika Murugu, Danna Gurari, Eunsol Choi, and Amy Pavel
A Critical Evaluation of Evaluations for Long-form Question Answering, ACL 2023
Fangyuan Xu*, Yixiao Song*, Mohit Iyyer, Eunsol Choi
[code]
Concise Answers to Complex Questions: Summarization of Long-form Answers, ACL 2023
Abhilash Potluri*, Fangyuan Xu*, Eunsol Choi
[code]
Modeling Exemplification in Long-form Question Answering via Retrieval, NAACL 2022
Shufan Wang, Fangyuan Xu, Laure Thompson, Eunsol Choi, Mohit Iyyer
[code]
How Do We Answer Complex Questions: Discourse Structure of Long-form Answers, ACL 2022
Fangyuan Xu, Jessy Junyi Li, Eunsol Choi
[code][website]
*=Equal contribution
Last updated: November 2024