activity
20242026
collaborators

7 papers

cs.LG2026

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection

Zhengyu Hu, Zheyuan Xiao, Linxin Song +10

LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the high…

stat.ML2026

On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits

Leo Maynard-Zhang, Zhihan Xiong, Kevin Jamieson +1

We study the fixed-budget best-arm identification (BAI) problem in non-stationary linear bandits. Concretely, given a fixed time budget , finite arm set $\mathcal{…

cs.CL2026

Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators

Zhengyu Hu, Jieyu Zhang, Zhihan Xiong +3

Despite the remarkable success of Large Language Models (LLMs), evaluating their outputs' quality regarding preference remains a critical challenge. While existing works usually le…

cs.LG2025

LoRe: Personalizing LLMs via Low-Rank Reward Modeling

Avinandan Bose, Zhihan Xiong, Yuejie Chi +3

Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning fr…

cs.LG2024

Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration

Avinandan Bose, Zhihan Xiong, Aadirupa Saha +2

Reinforcement Learning from Human Feedback (RLHF) is currently the leading approach for aligning large language models with human preferences. Typically, these models rely on exten…

cs.GT2024

Offline congestion games: How feedback type affects data coverage requirement

Haozhe Jiang, Qiwen Cui, Zhihan Xiong +2

This paper investigates when one can efficiently recover an approximate Nash Equilibrium (NE) in offline congestion games. The existing dataset coverage assumption in offline gener…