|
I am an undergraduate student studying Math and CS at Carleton College (MN), advised by Prof. Anna Rafferty. I am a SURF Research Fellow at Caltech, where I am fortunate to work with Prof. Anima Anandkumar and Dr. Rafał Kocielnik. I am a Researcher in the ULab at UIUC, advised by Prof. Jiaxuan You. I am currently applying for Ph.D. programs in Computer Science for the 2024–25 cycle. 韩芃睿 / Email / Google Scholar / GitHub / LinkedIn / Twitter |
|
|
[Oct. 2024] I am attending COLM 2024 to present our paper on synthetic data for debiasing |
|
My research interests center on understanding intelligence in both humans and machines. Currently, my focus is on investigating the cognitive limitations of foundation models and developing embodied and socially aware intelligent agents. |
|
Pengrui Han*, Peiyang Song*, Haofei Yu, and Jiaxuan You (* Equal Contribution) Findings of Empirical Methods in Natural Language Processing (EMNLP), 2024 code Motivated by the crucial cognitive phenomenon of A-not-B errors, we present the first systematic evaluation on the surprisingly vulnerable inhibitory control abilities of LLMs. We reveal that this weakness undermines LLMs' trustworthy reasoning capabilities across diverse domains, and introduce various mitigations. |
|
Pengrui Han*, Rafal Kocielnik*, Adhithya Saravanan,Roy Jiang, Or Sharir,and Anima Anandkumar (* Equal Contribution) Conference On Language Modeling (COLM), 2024 code We propose a light and efficient pipeline that enables both domain and non-domain experts to quickly generate synthetic debiasing data to mitigate specific or general bias in their models with parameter-efficient fine-tuning. |
|
Guanyu Lin*, Tao Feng*, Pengrui Han*, Ge Liu, Jiaxuan You (* Equal Contribution) System Demonstration Track of Empirical Methods in Natural Language Processing (EMNLP), 2024 Huggingface Live Demo: Link We propose a light and efficient pipeline that enables both domain and non-domain experts to quickly generate synthetic debiasing data to mitigate specific or general bias in their models with parameter-efficient fine-tuning. |
|
Tao Feng*, Pengrui Han*, Guanyu Lin*, Ge Liu, Jiaxuan You (* Equal Contribution) ICLR Workshop on How Far Are We From AGI, 2024 We introduce Thought-Retriever a novel model-agnostic algorithm that enables LLMs to effectively utilize external data without being limited by context length. |
|
Adhithya Saravanan, Rafal Kocielnik, Roy Jiang, Pengrui Han, and Anima Anandkumar NeurIPS Workshop on Failure Modes in the Age of Foundation Models, 2023 Proceedings of Machine Learning Research (PMLR) We explore the social biases in text-to-image diffusion models used in commercial applications like image editing. By analyzing models like Stable Diffusion, we uncover significant biases, emphasizing the need for careful consideration when adopting these technologies for broader use.
|
|
|
|