Scholar
Yong Lin
Google Scholar ID: M4g0ZvMAAAAJ
Princeton University
Citations & Impact
Citations
1,997
H-index
23
i10-index
28
Publications
20
Co-authors
19
list available
Contact
Publications
Resume (English only)
Academic Achievements
- The paper R-tuning won the Outstanding Paper Award at NAACL 2024; involved in multiple projects such as Goedel-Prover and its V2 version, ranking first on the PutnamBench leaderboard; the SelfMoA method also ranked first on the AlpacaEval 2.0 leaderboard.
Research Experience
- Currently a Postdoctoral Fellow at Princeton Language and Intelligence, collaborating with Chi Jin, Sanjeev Arora, and Danqi Chen. Prior to his PhD, he worked as a Senior Machine Learning Engineer at Alibaba from 2017 to 2021, where he developed industrial-level applications and gained insights into the challenges of deep models in an industrial setting.
Education
- PhD under the supervision of Professor Tong Zhang; recipient of Apple AI/ML PhD fellowship (2023) and Hong Kong PhD fellowship (2020). Specific degree, university, and time details not provided.
Background
- Research interests include formal math reasoning and post-training of large language models (LLMs). Specifically, enabling LLMs to reason using verifiable languages like LEAN, and training LLMs for automated theorem proving through the Goedel-Prover project. Also focused on enhancing traits such as helpfulness, harmlessness, and honesty in LLMs.
Miscellany
- Served as an Area Chair for ACL ARR in February 2025.
