用强化学习自动发现视觉语言模型的盲区，不依赖人工标注。
Discovering Failure Modes in Vision-Language Models using RL
- 构建问答代理，根据模型回答动态生成复杂问题。
- 在细粒度视觉细节上发现新失败模式，提升模型漏洞识别能力。
- 无需人工干预，适用于多种模型组合，可扩展性强。
视觉语言模型（VLMs）虽在多模态基准上表现优异，却常误解人类轻易理解的视觉概念，如计数、空间推理和视角理解。以往研究通过人工方式发现这些弱点，但成本高、难扩展且易受偏见影响，常忽略细微特征而关注显著对象，导致对模型脆弱性的理解不完整。为此，我们提出一种基于强化学习（RL）的框架，可自动发现任意候选VLM在给定数据分布下的失败模式或盲点，无需人工干预。该框架训练一个提问代理，根据候选VLM的回答自适应生成问题，逐步提高问题复杂度，聚焦细粒度视觉细节与独特技能组合，从而揭示模型难以应对的新失败模式。我们在多种模型组合上验证了该框架的广泛适用性与泛化能力。
原文摘要 · Abstract (English)
Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint understanding. Previous studies manually identified these weaknesses and found that they often stem from deficits in specific skills. However, such manual efforts are costly, unscalable, and subject to human bias, which often overlooks subtle details in favour of salient objects, resulting in an incomplete understanding of a model's vulnerabilities. To address these limitations, we propose a Reinforcement Learning (RL)-based framework to automatically discover the failure modes or blind spots of any ``candidate VLM'' on a given data distribution without human intervention. Our framework trains a questioner agent that adaptively generates queries based on the candidate VLM's responses to elicit incorrect answers. Our approach increases question complexity by focusing on fine-grained visual details and distinct skill compositions as training progresses, consequently identifying novel failure modes in which VLMs struggle. We demonstrate the broad applicability of our framework by showcasing its generalizability across various model combinations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。