自動運転における視覚言語モデルの幻覚を低ランク分解で軽減する手法
A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving
複数の視覚言語モデルが生成したキャプションを、文埋め込み行列の低ランク分解で得られるスパース残差の大きさでランク付けし、幻覚の少ないキャプションを選別する手法を提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Keke Long, Jiacheng Guo, Tianyun Zhang, Hongkai Yu, Xiaopeng Li
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
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.
