3 papers
cs.LG2026
VERA: Verdict-Conditioned Reliability for Adaptive LLM Judges
Qiushui Xu, Syamil Mohd Razak, Tao Yuan +1
Accurately estimating judgment reliability is a central challenge in adapting LLM judges to newly verified feedback while preserving previously learned behavior. However, existing…
cs.LG2025
In-Context Compositional Q-Learning for Offline Reinforcement Learning
Qiushui Xu, Yuhao Huang, Yushu Jiang +4
Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inad…
cs.LG2024
Unveiling Markov Heads in Pretrained Language Models for Offline Reinforcement Learning
Wenhao Zhao, Qiushui Xu, Linjie Xu +4
Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL)…