mlsanityData to 14 Oct 2026

The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs

arXiv 2509.13379 ↗First posted 16 Sep 2025cs.AI cs.CVcited by 2

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical dimension of uncertainty quantification has received insufficient attention. Therefore, unlike prior conformal prediction studies that focused on limited settings, we conduct a comprehensive uncertainty benchmarking study, evaluating 18 state-of-the-art VLMs (open and closed-source) across 6 multimodal datasets with 3 distinct scoring functions. For closed-source models lacking token-level logprob access, we develop and validate instruction-guided likelihood proxies. Our findings demonstrate that larger models consistently exhibit better uncertainty quantification; models that know more also know better what they don't know. More certain models achieve higher accuracy, while mathematical and reasoning tasks elicit poorer uncertainty performance across all models compared to other domains. This work establishes a foundation for reliable uncertainty evaluation in multimodal systems.

Key facts. Cited by 2 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 22 of its 37 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

22 of 37 references.

References · 22

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  7. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  8. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  9. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  10. 2016A Diagram Is Worth A Dozen Imagescited by 804
  11. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  12. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 556
10 more
  1. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Datasetcited by 526
  2. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 512
  3. 2020Classification with Valid and Adaptive Coveragecited by 396
  4. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  5. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 272
  6. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 138
  7. 2025MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoningcited by 45
  8. 2023DelucionQA: Detecting Hallucinations in Domain-specific Question Answeringcited by 43
  9. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25
  10. 2024WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasetscited by 2
  2. 2026Uncertainty-Aware Decision Making in Multimodal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Uncertainty-Aware Evaluation for Vision-Language Models
  2. 2025Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models
  3. 2026VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Models
  4. 2026VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
  5. 2026Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation
  6. 2026FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty
  7. 2024Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models
  8. 2025Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere