Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain
On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Abstract (arXiv)
Multimodal large language models (MLLMs) have shown strong potential for medical Visual Question Answering (VQA), yet they remain prone to hallucinations, defined as generating responses that contradict the input image, posing serious risks in clinical settings. Current hallucination detection methods, such as Semantic Entropy (SE) and Vision-Amplified Semantic Entropy (VASE), require 10 to 20 stochastic generations per sample together with an external natural language inference model for semantic clustering, making them computationally expensive and difficult to deploy in practice. We observe that hallucinated responses exhibit a distinctive signature directly in the model's own log-probabilities: inconsistent token-level confidence and weak sensitivity to visual evidence. Based on this observation, we propose Confidence-Evidence Bayesian Gain (CEBaG), a deterministic hallucination detection method that requires no stochastic sampling, no external models, and no task-specific hyperparameters. CEBaG combines two complementary signals: token-level predictive variance, which captures inconsistent confidence across response tokens, and evidence magnitude, which measures how much the image shifts per-token predictions relative to text-only inference. Evaluated across four medical MLLMs and three VQA benchmarks (16 experimental settings), CEBaG achieves the highest AUC in 13 of 16 settings and improves over VASE by 8 AUC points on average, while being fully deterministic and self-contained. https://github.com/masadi-99/CEBaG
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 26 of its 31 references that are in the map. First posted on arXiv 23 Mar 2026.
Builds on
26 of 31 references.
Closest ancestors · 10
Same direction, newest first
- 2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation18 Nov
- 2024Reference-free Hallucination Detection for Large Vision-Language Models11 Aug
- 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding27 Mar
- 2024Multi-Modal Hallucination Control by Visual Information Grounding20 Mar
- 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
- 2023Hallucination Augmented Contrastive Learning for Multimodal Large Language Model12 Dec
- 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
- 2023HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data22 Nov
- 2023Woodpecker: Hallucination Correction for Multimodal Large Language Models24 Oct
- 2023Detecting and Preventing Hallucinations in Large Vision Language Models11 Aug
Other references · 16
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
- 2022Language Models (Mostly) Know What They Knowcited by 1,856
- 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
- 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
- 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
- 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
- 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
- 2025MedGemma Technical Reportcited by 436
- 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
- 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 259
- 2024Capabilities of Gemini Models in Medicinecited by 237
- 2024HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scalecited by 200
4 more
- 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 156
- 2024GREEN: Generative Radiology Report Evaluation and Error Notationcited by 128
- 2024A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicinecited by 45
- 2024GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosiscited by 29
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025UniVRSE: Unified Vision-conditioned Response Semantic Entropy for Hallucination Detection in Medical Vision-Language Models
- 2026VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering
- 2026V-Loop: Visual Logical Loop Verification for Hallucination Detection in Medical Visual Question Answering
- 2026Detecting Clinical Hallucinations in LVLMs via Counterfactual Visual Grounding Uncertainty
- 2024Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
- 2026PROVE: Proof-guided Regime-aware Operator Verification for Hallucination Detection in Medical Visual Question Answering
- 2025HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models
- 2025Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate