Concept Incongruence is Key to AI Safety and Creativity (July, 2025)
⚡️Ever asked an LLM-as-Marilyn Monroe about the 2020 election? Our paper calls this concept incongruence, common in AI and human creativity. Read my blog to learn what we found, why it matters for AI safety and creativity, and what's next.
Hi! I'm Xiaoyan(Elena) Bai
柏 晓琰
I am currently a first-year PhD student in CS at University of Chicago , advised by Chenhao Tan . I am also a member of Chicago Human+AI lab.
Before that, I earned B.E in Computer Science at CSE at Univeristy of Michigan, Ann Arbor. During my undergrad study, I was honored to be a member of Language and Information Technologies (LIT) lab group to work with Rada Mihalcea. I also worked on NLP inference time efficiency in Atul Prakash's group. I am interested in doing research in Natural Language Processing. At the same time, I like photography and Game Design & Development. Check the games I made!
Research Interest: As machine learning continues to advance, so does the potential for the digital divide and inequality to widen. These issues motivate my research in building transparent, efficient, and more accessible tools for social good. I believe this can be done by building interpretable models or building more cost-efficient methods
Publications
Concept Incongruence: An Exploration of Time and Death in Role Playing (preprint, 2025)
Xiaoyan Bai, Ike Peng*, Aditya Singh*, Chenhao Tan
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity (ICML, 2024) Oral
Andrew Lee, Xiaoyan Bai, Itamar Pres, Martin Wattenberg, Jonathan K. Kummerfeld, Rada Mihalcea
Learn To be Efficient: Build Structured Sparsity in Large Language Models (Neurips, 2024) Spotlight
Haizhong Zheng, Xiaoyan Bai, Xueshen Liu, Z. Morley Mao, Beidi Chen, Fan Lai, Atul Prakash
Blog
