5 papers
The Complexity of Tullock Contests
Yu He, Fan Yao, Yang Yu +3
Despite the extensive literature on Tullock contests, computational results for the general model with heterogeneous contestants remain scarce. This paper studies the algorithmic c…
How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics
Yurong Chen, Yu He, Michael I. Jordan +1
Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference polic…
Policy Design for Two-sided Platforms with Participation Dynamics
Haruka Kiyohara, Fan Yao, Sarah Dean
In two-sided platforms (e.g., video streaming or e-commerce), viewers and providers engage in interactive dynamics: viewers benefit from increases in provider populations, while pr…
Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms
Fan Yao, Yiming Liao, Jingzhou Liu +4
On User-Generated Content (UGC) platforms, recommendation algorithms significantly impact creators' motivation to produce content as they compete for algorithmically allocated user…
Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Dueling
Yuwei Cheng, Fan Yao, Xuefeng Liu +1
This paper studies Learning from Imperfect Human Feedback (LIHF), addressing the potential irrationality or imperfect perception when learning from comparative human feedback. Buil…