4 papers
Robust Multimodal Large Language Models Against Modality Conflict
Zongmeng Zhang, Wengang Zhou, Jie Zhao +1
Despite the impressive capabilities of multimodal large language models (MLLMs) in vision-language tasks, they are prone to hallucinations in real-world scenarios. This paper inves…
Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
Jianfeng Cai, Wengang Zhou, Zongmeng Zhang +3
Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding.However, hallucination, where the model generates plausible yet incorrect outputs,…
BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?
Zongmeng Zhang, Jinhua Zhu, Wengang Zhou +3
Dense retrieval, which aims to encode the semantic information of arbitrary text into dense vector representations or embeddings, has emerged as an effective and efficient paradigm…
Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
Zongmeng Zhang, Yufeng Shi, Jinhua Zhu +4
Trustworthiness is an essential prerequisite for the real-world application of large language models. In this paper, we focus on the trustworthiness of language models with respect…