Pengrui Han

According to our database, Pengrui Han authored at least 4 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance.

Guanyu Lin, Tao Feng, Pengrui Han, Ge Liu, Jiaxuan You

CoRR, 2024

ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs.

Pengrui Han, Rafal Kocielnik, Adhithya Prakash Saravanan, Roy Jiang, Or Sharir, Anima Anandkumar

CoRR, 2024

In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models.

Pengrui Han, Peiyang Song, Haofei Yu, Jiaxuan You

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023

Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models.

Adhithya Prakash Saravanan, Rafal Kocielnik, Roy Jiang, Pengrui Han, Anima Anandkumar

Proceedings of the Proceedings on "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models" at NeurIPS 2023 Workshops, 2023