[about]   [papers]   [travels]   [talks]  


my face


Chenglei Si (チェンレイ・シ)

[email] [scholar] [twitter] [github]
2nd Year PhD at Stanford NLP

About

 At Stanford, I'm advised by the wonderful Tatsu Hashimoto and Diyi Yang. Before coming to Stanford, I did my undergrad at the University of Maryland where I was advised by Jordan Boyd-Graber. I also had the fortune to work with many amazing research mentors and collaborators, including Michael Bernstein, Hal Daumé III, He He, Danqi Chen, Sherry Wu, Zhiyuan Liu, Min-Yen Kan, and many others.

I'm interested in how LLMs can transform scientific research, and new forms of human-AI co-intelligence. Towards this end, I split my time between working with LLMs and running human studies. When not writing papers, I also write research related threads for fun.

Research style: I've come to the realization that I'm most productive when focusing on only 1-2 projects every year. And I prefer projects that are more ambitious and risky in nature (which also tend to be longer-term). This means that I have to turn down all the collaboration requests that don't fall into this category -- I'm sorry!

Selected Papers
  • Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
    Chenglei Si, Diyi Yang, Tatsunori Hashimoto
    ICLR 2025 [paper] [code] [tweet] [Nature News] [Newsweek] [Synced]

  • Design2Code: How Far Are We From Automating Front-End Engineering?
    Chenglei Si*, Yanzhe Zhang*, Zhengyuan Yang, Ruibo Liu, Diyi Yang
    NAACL 2025 [paper] [code] [project page] [tweet] [WorldofAI]

  • Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong
    Chenglei Si, Navita Goyal, Sherry Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, Jordan Boyd-Graber
    NAACL 2024 [paper] [tweet]

  • Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations
    Chenglei Si*, Dan Friedman*, Nitish Joshi, Shi Feng, Danqi Chen, He He
    ACL 2023 [paper] [code] [tweet] [OpenReview]

  • Prompting GPT-3 To Be Reliable
    Chenglei Si, Zhe Gan, Zhengyuan Yang, Shuohang Wang, Jianfeng Wang, Jordan Boyd-Graber, Lijuan Wang
    ICLR 2023 [paper] [code] [tweet] [video]

Talks
  • Fall 2024: The Dream of Automating Research (Part 1)
    Stanford, USC, MIT, Northeastern, MILA, Intel, Samaya AI
    [slides] [podcast]


Conference Travels
  • April 2025, ICLR @ Singapore
  • Dec 2024, NeurIPS @ Vancouver
  • June 2024, NAACL @ Mexico City
  • Oct 2023, UIST @ San Francisco
  • July 2023, ACL @ Toronto
  • May 2023, ICLR @ Kigali
  • Dec 2022, EMNLP @ Abu Dhabi
  • July 2022, NAACL @ Seattle