collaborators

8 papers

cs.CV2026

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement

Zhenxin Qin, Qiang Li, Qingzhuo Wang +3

Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that co…

cs.LG2026

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions

Qingzhuo Wang, Ruiyang Qin, Zhenxin Qin +2

Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unifie…

cs.CV2026

Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift

Zhihua Wei, Qiang Li, Jian Ruan +4

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, add…

cs.IR2025

Harnessing Pairwise Ranking Prompting Through Sample-Efficient Ranking Distillation

Junru Wu, Le Yan, Zhen Qin +6

While Pairwise Ranking Prompting (PRP) with Large Language Models (LLMs) is one of the most effective zero-shot document ranking methods, it has a quadratic computational complexit…

cs.CL2025

Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation

Jiaming Shen, Ran Xu, Yennie Jun +6

Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. They are trained using preference datasets where each example consists of one inpu…

cs.CL2025

RRM: Robust Reward Model Training Mitigates Reward Hacking

Tianqi Liu, Wei Xiong, Jie Ren +15

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to sp…