Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models

A new study introduces the Intervene-All-Paths framework, aimed at mitigating hallucinations in Large Vision-Language Models (LVLMs) by addressing the interplay of various causal pathways. This research highlights that hallucinations stem from multiple sources, including image-to-input-text and text-to-text interactions, and proposes targeted interventions for different question-answer alignment formats.

Recent advancements in Large Vision-Language Models (LVLMs) have led to the introduction of the Draft and Refine (DnR) framework, which enhances the models' reasoning capabilities by quantifying their reliance on visual evidence through a question-conditioned utilization metric. This approach aims to reduce ungrounded or hallucinated responses by refining initial drafts with targeted feedback from visual experts.