Discovering Failure Modes in Vision-Language Models using RL
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSpatial ReasoningSimilar Papers 제목 키워드 기반
What could go wrong? Discovering and describing failure modes in computer vision
Deep learning models are effective, yet brittle. Even carefully trained, their behavior tends to be hard to predict when confronted with out-of-distribution samples. In this work, our goal is to propose a simple yet effe…
Semantic SegmentationDiscover and Mitigate Multiple Biased Subgroups in Image Classifiers
Machine learning models can perform well on in-distribution data but often fail on biased subgroups that are underrepresented in the training data, hindering the robustness of models for reliable applications. Such subgr…
Dimensionality ReductionSubgroup DiscoveryFailures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models
In large deep neural networks that seem to perform surprisingly well on many tasks, we also observe a few failures related to accuracy, social biases, and alignment with human values, among others. Therefore, before depl…
Deep Reinforcement LearningUnderstanding Failures of Deep Networks via Robust Feature Extraction
Traditional evaluation metrics for learned models that report aggregate scores over a test set are insufficient for surfacing important and informative patterns of failure over features and instances. We introduce and st…
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search
Text-guided diffusion models (TDMs) are widely applied but can fail unexpectedly. Common failures include: (i) natural-looking text prompts generating images with the wrong content, or (ii) different random samples of th…
Adversarial AttackEfficient ExplorationImage Generation