Yike Wang

Hiii, welcome to my homepage 👋🏻

I am a second-year Ph.D. student at the University of Washington, advised by Professor Hannaneh Hajishirzi and Professor Yulia Tsvetkov. I am currently interested in downscaling language models.

Before that, I received my B.A. in computer science and applied mathematics and M.S. in computer science at UC Berkeley, where I was fortunate to be advised by Professor Anca Dragan, Professor Joseph Gonzalez, and Professor Dan Klein. I also interned at ByteDance.

Email  /  Twitter  /  Google Scholar  /  GitHub

Research

💬 Don't Throw Away Your Pretrained Model

🪿 ScienceMeter: Tracking Scientific Knowledge Updates in Language Models

🍒 Data Swarms: Optimizable Generation of Synthetic Evaluation Data

⛲️ Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

🛠️ When One LLM Drools, Multi-LLM Collaboration Rules

💪🏻 Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

🪴 Teaching LLMs to Abstain across Languages via Multilingual Feedback

🥂 Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration

🐑 Resolving Knowledge Conflicts in Large Language Models

🎧 Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media

Teaching

UC Berkeley Data C100/200 Principles and Techniques of Data Science

Discussion Slides and Notes

Source