Uncertainty-Aware Evaluation for Vision-Language Models
Vision-Language Models like GPT-4, LLaVA, and CogVLM have surged in popularity recently due to their impressive performance in several vision-language tasks. Current evaluation methods, however, overlook an essential component: uncertainty, which is crucial for a comprehensive assessment of VLMs. Addressing this oversight, we present a benchmark incorporating uncertainty quantification into evaluating VLMs. Our analysis spans 20+ VLMs, focusing on the multiple-choice Visual Question Answering (VQA) task. We examine models on 5 datasets that evaluate various vision-language capabilities. Using conformal prediction as an uncertainty estimation approach, we demonstrate that the models' uncertainty is not aligned with their accuracy. Specifically, we show that models with the highest accuracy may also have the highest uncertainty, which confirms the importance of measuring it for VLMs. Our empirical findings also reveal a correlation between model uncertainty and its language model part.
Code (1)
Tasks
Conformal PredictionLanguage ModelingLanguage ModellingMultiple-choiceQuestion AnsweringUncertainty QuantificationVisual Question AnsweringVisual Question Answering (VQA)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its ow…
Decision-Aware Uncertainty Evaluation of Vision-Language Model-Based Early Action Anticipation for Human-Robot Interaction
Robots in shared workspaces must interpret human actions from partial, ambiguous observations, where overconfident early predictions can lead to unsafe or disruptive interaction. This challenge is amplified in egocentric…
Action AnticipationAction RecognitionCXR-Agent: Vision-language models for chest X-ray interpretation with uncertainty aware radiology reporting
Recently large vision-language models have shown potential when interpreting complex images and generating natural language descriptions using advanced reasoning. Medicine's inherently multimodal nature incorporating sca…
Data AugmentationPhrase GroundingReasoning under Ambiguity: Uncertainty-Aware Multilingual Emotion Classification under Partial Supervision
Contemporary knowledge-based systems increasingly rely on multilingual emotion identification to support intelligent decision-making, yet they face major challenges due to emotional ambiguity and incomplete supervision. …
Emotion ClassificationEmotion RecognitionUncertainty-Aware Knowledge Distillation for Multimodal Large Language Models
Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is chall…
Knowledge Distillation