Jiayi Geng
jiayig@princeton.edu
I am a second year Computer Science master’s student at Princeton University, advised by Prof. Danqi Chen. During my master’s, I also work closely with Prof. Thomas L. Griffiths.
My research goal is to explore and enable machines to engage in better deliberation. More specifically, I am interested in (1) drawing inspiration from cognitive psychology to understand the deep interconnection between machines and humans, particularly focusing on the interplay between memory and reasoning, and (2) designing appropriate algorithms and methods to push the limits of LLM deliberation.
Before Princeton, I received my Bachelor’s degree at McGill University, advised by Prof. Xue (Steve) Liu and Prof. Eric D. Kolaczyk.
News
| 2024-10 | Our new preprint: Mind Your Step (by Step): Chain-of-Thought Can Reduce Performance on Tasks where Thinking Makes Humans Worse is out! |
|---|---|
| 2024-05 | Our paper Language Models as Science Tutors has been accepted by ICML 2024! |
| 2023-09 | Started my Master study at Princeton University!  |
Selected publications
(* indicates equal contribution)
-
-
Mind your step (by Step): Chain-of-thought Can Reduce Performance on Tasks Where Thinking Makes Humans WorsearXiv preprint 2410.21333, 2024 -
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N SamplingarXiv preprint 2410.16033, 2024 -
Large language Models Assume People are More Rational than We Really arearXiv preprint 2406.17055, 2024 -
