A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving
This addresses the critical issue of false details in VLM outputs for autonomous driving, offering a practical, real-time solution, though it is incremental as it builds on existing captioning and ranking techniques.
The paper tackles the problem of hallucination in Vision Language Models (VLMs) for autonomous driving by proposing a low-rank method to automatically rank and select hallucination-free captions without external references, achieving 87% selection accuracy and reducing inference time by 51-67%.
Vision Language Models (VLMs) are increasingly used in autonomous driving to help understand traffic scenes, but they sometimes produce hallucinations, which are false details not grounded in the visual input. Detecting and mitigating hallucinations is challenging when ground-truth references are unavailable and model internals are inaccessible. This paper proposes a novel self-contained low-rank approach to automatically rank multiple candidate captions generated by multiple VLMs based on their hallucination levels, using only the captions themselves without requiring external references or model access. By constructing a sentence-embedding matrix and decomposing it into a low-rank consensus component and a sparse residual, we use the residual magnitude to rank captions: selecting the one with the smallest residual as the most hallucination-free. Experiments on the NuScenes dataset demonstrate that our approach achieves 87% selection accuracy in identifying hallucination-free captions, representing a 19% improvement over the unfiltered baseline and a 6-10% improvement over multi-agent debate method. The sorting produced by sparse error magnitudes shows strong correlation with human judgments of hallucinations, validating our scoring mechanism. Additionally, our method, which can be easily parallelized, reduces inference time by 51-67% compared to debate approaches, making it practical for real-time autonomous driving applications.