Fangyuan Xu

👩‍💻

I am a second-year PhD student in Computer Science at the University of Texas at Austin, working with Eunsol Choi. I am interested in natrual language processing and machine learning.

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. Previously, I worked as a Machine Learning Engineer at Twitter.

Publications

KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions, Arxiv 2024
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]

Understanding Retrieval Augmentation for Long-Form Question Answering, Arxiv 2023
Hung-Ting Chen, Fangyuan Xu*, Shane Arora*, Eunsol Choi
[code]

A Critical Evaluation of Evaluations for Long-form Question Answering, ACL 2023 (long)
Fangyuan Xu*, Yixiao Song*, Mohit Iyyer, Eunsol Choi
[code]

Concise Answers to Complex Questions: Summarization of Long-form Answers, ACL 2023 (long)
Abhilash Potluri*, Fangyuan Xu*, Eunsol Choi
[code]

Modeling Exemplification in Long-form Question Answering via Retrieval, NAACL 2022 (long)
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 (long)
Fangyuan Xu, Jessy Junyi Li, Eunsol Choi
[code][website]

*=Equal contribution