# Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification

arXiv: https://arxiv.org/abs/2602.05535 · HTML: https://mlsanity.com/paper/2602.05535/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 18 of its 100 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [Large Language Models Must Be Taught to Know What They Don't Know](https://mlsanity.com/paper/2406.08391/) (2024)
- [SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization](https://mlsanity.com/paper/2505.12346/) (2025)
- [International AI Safety Report](https://mlsanity.com/paper/2501.17805/) (2025)
- [Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach](https://mlsanity.com/paper/2412.18108/) (2024)
- [Estimating LLM Uncertainty with Evidence](https://mlsanity.com/paper/2502.00290/) (2025)
- [Towards Uncovering How Large Language Model Works: An Explainability Perspective](https://mlsanity.com/paper/2402.10688/) (2024)
- [Semantic Consistency for Assuring Reliability of Large Language Models](https://mlsanity.com/paper/2308.09138/) (2023)
- [Calibrating LLMs with Information-Theoretic Evidential Deep Learning](https://mlsanity.com/paper/2502.06351/) (2025)
- [Are vision language models robust to uncertain inputs?](https://mlsanity.com/paper/2505.11804/) (2025)

## Built on by (most cited first, 6 of 6)

- [GENSR: Symbolic Regression Based in Equation Generative Space](https://mlsanity.com/paper/2602.20557/) (2026)
- [Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking](https://mlsanity.com/paper/2608.01021/) (2026)
- [Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Models in Clinical Text](https://mlsanity.com/paper/2605.28740/) (2026)
- [Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate](https://mlsanity.com/paper/2608.03648/) (2026)
- [AnyTrack: Unifying Visual Object Tracking with Any Modalities](https://mlsanity.com/paper/2608.06773/) (2026)
- [LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search](https://mlsanity.com/paper/2608.09152/) (2026)

## Abstract (arXiv)

%Large vision-language models (LVLMs) have shown substantial advances in multimodal understanding and generation. However, when presented with incompetent or adversarial inputs, they frequently produce unreliable or even harmful content, such as fact hallucinations or dangerous instructions. This misalignment with human expectations, referred to as misbehaviors of LVLMs, raises serious concerns for deployment in critical applications. These misbehaviors are found to stem from epistemic uncertainty, specifically either conflicting internal knowledge or the absence of supporting information. However, existing uncertainty quantification methods, which typically capture only overall epistemic uncertainty, have shown limited effectiveness in identifying such issues. To address this gap, we propose Evidential Uncertainty Quantification (EUQ), a fine-grained method that captures both information conflict and ignorance for effective detection of LVLM misbehaviors. In particular, we interpret features from the model output head as either supporting (positive) or opposing (negative) evidence. Leveraging Evidence Theory, we model and aggregate this evidence to quantify internal conflict and knowledge gaps within a single forward pass. %We extensively evaluate our method across four categories of misbehavior, including hallucinations, jailbreaks, adversarial vulnerabilities, and out-of-distribution (OOD) failures, using state-of-the-art LVLMs, and find that EUQ consistently outperforms strong baselines, showing that hallucinations correspond to high internal conflict and OOD failures to high ignorance. Furthermore, layer-wise evidential uncertainty dynamics analysis helps interpret the evolution of internal representations from a new perspective. The source code is available at https://github.com/HT86159/EUQ.