自動運転VLM向け合成MCQAにおけるテキストバイアスの低減
Reducing Text Bias in Synthetically Generated MCQAs for VLMs in Autonomous Driving
自動運転向けVLM評価用の合成MCQAベンチマークに潜む言語的手がかりを除去し、視覚情報に基づく推論を強制する手法を提案した。
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: Sutej Kulgod, Sean Ye, Sanchit Tanwar, Christoffer Heckman
分類: cs.LG, cs.CL, cs.RO
原文アブストラクト
Multiple Choice Question Answering (MCQA) benchmarks are an established standard for measuring Vision Language Model (VLM) performance in driving tasks. However, we observe the known phenomenon that synthetically generated MCQAs are highly susceptible to hidden textual cues that allow models to exploit linguistic patterns rather than visual context. Our results show that a VLM fine-tuned on such data can achieve accuracy comparable to human-validated benchmarks even without visual input. Our proposed method reduces blind accuracy from +66.9% above random to +2.9%, eliminating the vast majority of exploitable textual shortcuts. By decoupling the correct answer from linguistic artifacts and employing a curriculum learning strategy, we force the model to rely on visual grounding, ensuring that performance accurately reflects perceptual understanding.
