12 citations · 21 across the 24 of their papers we have counts for
7 papers · 1 filter
LegalRewardBench: Benchmarking Reward Models for Legal Preference Evaluation
Hui Huang, Jie Zhou, Hongli Zhou +7
Reward models are central to preference alignment for legal tasks, yet existing reward model benchmarks are still primarily centered on general-domain preferences. In this work, we…
RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems
Yuchen Song, Andong Chen, Wenxin Zhu +2
LLM-based multi-agent systems (MASs) have shown strong potential for solving complex tasks, but most assume that task requirements are sufficiently specified before execution. In p…
User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
Mufan Xu, Kehai Chen, Jiahao Hu +4
Emotional support plays an important role in dialogue systems, and its success depends on adapting to a user's evolving and implicit needs across multi-turn interactions while leve…
Long-form RewardBench: Evaluating Reward Models for Long-form Generation
Hui Huang, Yancheng He, Wei Liu +7
The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to evaluate reward models i…
Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
Hongli Zhou, Hui Huang, Rui Zhang +5
Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evalu…
Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models
Mufan Xu, Kehai Chen, Xuefeng Bai +4
Existing policy-gradient methods for auto-regressive language models typically select subsequent tokens one at a time as actions in the policy. While effective for many generation…
Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling
Andong Chen, Wenxin Zhu, Qiuyu Ding +3
Chain-of-Thought reasoning has driven large language models to extend from thinking with text to thinking with images and videos. However, different modalities still have clear lim…