Yeyun Gong

Yeyun Gong

Auto-generated profile, based on publicly available information

Yeyun Gong

Microsoft Research Asia, Beijing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2023
Verified
Conference Paper
Open access
PDF file
XMXinbei Ma
Xinbei Ma
YGYeyun Gong
Yeyun Gong
PHPengcheng He
Pengcheng He
HZHai Zhao
Hai Zhao
NDNan Duan
Nan Duan
Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, Nan Duan. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

1 January 2024
Verified
Conference Paper
Open access
PDF file
XHXingwei He
Xingwei He
ZLZhenghao Lin
Zhenghao Lin
YGYeyun Gong
Yeyun Gong
AJA-Long Jin
A-Long Jin
HZHang Zhang
Hang Zhang
WCWeizhu Chen
Weizhu Chen
Xingwei He, Zhenghao Lin, Yeyun Gong, A-Long Jin, Hang Zhang, Chen Lin, Jian Jiao, Siu Ming Yiu, Nan Duan, Weizhu Chen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track). 2024.

23 June 2025 in Science China Information Sciences
Verified
Journal Article
Closed access
PDF file
YLYi Luo
Yi Luo
LSLinghang Shi
Linghang Shi
YLYihao Li
Yihao Li
AZAobo Zhuang
Aobo Zhuang
YGYeyun Gong
Yeyun Gong
CLChen Lin
Chen Lin

1 January 2024
Verified
Conference Paper
Open access
PDF file
YHYiming Huang
Yiming Huang
ZLZhenghao Lin
Zhenghao Lin
XLXiao Liu
Xiao Liu
YGYeyun Gong
Yeyun Gong
SLShuai Lu
Shuai Lu
WCWeizhu Chen
Weizhu Chen
Yiming Huang, Zhenghao Lin, Xiao Liu, Yeyun Gong, Shuai Lu, Fangyu Lei, Yaobo Liang, Yelong Shen, Chen Lin, Nan Duan, Weizhu Chen. Findings of the Association for Computational Linguistics ACL 2024. 2024.

9 October 2025 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
CYChenyuan Yang
Chenyuan Yang
XLXuheng Li
Xuheng Li
RMRakib Hossain Misu
Rakib Hossain Misu
JYJianan Yao
Jianan Yao
WCWeidong Cui
Weidong Cui
SLShan Lu
Shan Lu
Generative AI has shown its value for many software engineering tasks. Still in its infancy, large language model (LLM)-based proof generation lags behind LLM-based code generation. In this paper, we present AutoVerus. AutoVerus uses LLMs to automatically generate correctness proof for Rust code. AutoVerus is designed to match the unique features of Verus, a verification tool that can prove the correctness of Rust code using proofs and specifications also written in Rust. AutoVerus consists of a network of agents that are crafted and orchestrated to mimic human experts' three phases of proof construction: preliminary proof generation, proof refinement guided by generic tips, and proof debugging guided by verification errors. To thoroughly evaluate AutoVerus and help foster future research in this direction, we have built a benchmark suite of 150 non-trivial proof tasks, based on existing code-generation benchmarks and verification benchmarks. Our evaluation shows that AutoVerus can automatically generate correct proof for more than 90% of them, with more than half of them tackled in less than 30 seconds or 3 LLM calls.

30 April 2023
Verified
Conference Paper
Open access
ZLZhenghao Lin
Zhenghao Lin
YGYeyun Gong
Yeyun Gong
XLXiao Liu
Xiao Liu
HZHang Zhang
Hang Zhang
CLChen Lin
Chen Lin
NDNan Duan
Nan Duan
Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student performs. However, this expectation does not always come true. It is common that a strong teacher model results in a bad student via distillation due to the nonnegligible gap between teacher and student. To bridge the gap, we propose PROD, a PROgressive Distillation method, for dense retrieval. PROD consists of a teacher progressive distillation and a data progressive distillation to gradually improve the student. To alleviate catastrophic forgetting, we introduce a regularization term in each distillation process. We conduct extensive experiments on seven datasets including five widely-used publicly available benchmarks: MS MARCO Passage, TREC Passage 19, TREC Document 19, MS MARCO Document, and Natural Questions, as well as two industry datasets: Bing-Rel and Bing-Ads. PROD achieves the state-of-the-art in the distillation methods for dense retrieval. Our 6-layer student model even surpasses most of the existing 12-layer models on all five public benchmarks. The code and models are released in https://github.com/microsoft/SimXNS.