V-Loop: Visual Logical Loop Verification for Hallucination Detection in Medical Visual Question Answering

• URL: http://arxiv.org/abs/2601.18240v1
• Date: Mon, 26 Jan 2026 07:46:41 GMT
• Title: V-Loop: Visual Logical Loop Verification for Hallucination Detection in Medical Visual Question Answering
• Abstract summary: We propose a training-free and plug-and-play framework for hallucination detection in medical visual question answering.<n>V-Loop forms a visually grounded logical loop to verify factual correctness.<n>It consistently outperforms existing introspective methods, remains highly efficient, and further boosts uncertainty-based approaches when used in combination.
• Score: 8.994256499686863
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable capability in assisting disease diagnosis in medical visual question answering (VQA). However, their outputs remain vulnerable to hallucinations (i.e., responses that contradict visual facts), posing significant risks in high-stakes medical scenarios. Recent introspective detection methods, particularly uncertainty-based approaches, offer computational efficiency but are fundamentally indirect, as they estimate predictive uncertainty for an image-question pair rather than verifying the factual correctness of a specific answer. To address this limitation, we propose Visual Logical Loop Verification (V-Loop), a training-free and plug-and-play framework for hallucination detection in medical VQA. V-Loop introduces a bidirectional reasoning process that forms a visually grounded logical loop to verify factual correctness. Given an input, the MLLM produces an answer for the primary input pair. V-Loop extracts semantic units from the primary QA pair, generates a verification question by conditioning on the answer unit to re-query the question unit, and enforces visual attention consistency to ensure answering both primary question and verification question rely on the same image evidence. If the verification answer matches the expected semantic content, the logical loop closes, indicating factual grounding; otherwise, the primary answer is flagged as hallucinated. Extensive experiments on multiple medical VQA benchmarks and MLLMs show that V-Loop consistently outperforms existing introspective methods, remains highly efficient, and further boosts uncertainty-based approaches when used in combination.

Related papers

• Detecting Clinical Hallucinations in LVLMs via Counterfactual Visual Grounding Uncertainty [22.008964207160663]
  We present a vision-traceable hallucination detection framework that audits arbitrary LVLM responses via visual evidence grounding.<n>We extract visually verifiable entities and use a medical-domain-adapted Qwen-VL grounding verifier to localize each entity on the input image.<n>Experiments on multiple medical imaging modalities and LVLM backbones demonstrate that our method consistently improves hallucination detection performance.
  arXiv  Detail & Related papers  (2026-06-26T18:15:38Z)
• VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering [27.827862126990553]
  Hallucinations pose risks to clinical decision-making and necessitate effective detection.<n>Existing introspective detection methods primarily perform uncertainty estimation or logical verification.<n>We propose VIHD, a Visual Intervention-based Hallucination Detection method.
  arXiv  Detail & Related papers  (2026-05-20T06:14:45Z)
• Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain [6.272224314406867]
  Multimodal large language models (MLLMs) have shown strong potential for medical Visual Question Answering (VQA)<n>They remain prone to hallucinations, defined as generating responses that contradict the input image, posing serious risks in clinical settings.<n>Current hallucination detection methods, such as Semantic Entropy (SE) and Vision-Amplified Semantic Entropy (VASE), require 10 to 20 generations per sample together with an external natural language inference model for semantic clustering, making them expensive and difficult to deploy in practice.<n>We propose a deterministic detection method that requires no sampling, no external models, and no task-
  arXiv  Detail & Related papers  (2026-03-23T08:29:53Z)
• S-Chain: Structured Visual Chain-of-Thought For Medicine [81.97605645734741]
  We introduce S-Chain, the first large-scale dataset of 12,000 expert-annotated medical images with bounding boxes and structured visual CoT (SV-CoT)<n>The dataset further supports 16 languages, totaling over 700k VQA pairs for broad multilingual applicability.<n>S-Chain establishes a new benchmark for grounded medical reasoning and paves the way toward more trustworthy and explainable medical vision-language models.
  arXiv  Detail & Related papers  (2025-10-26T15:57:14Z)
• Saliency Guided Longitudinal Medical Visual Question Answering [9.991158264639209]
  Longitudinal medical visual question answering (Diff-VQA) requires comparing paired studies from different time points.<n>We propose a saliency-guided encoder-decoder for chest X-ray Diff-VQA that turns post-hoc saliency into actionable supervision.
  arXiv  Detail & Related papers  (2025-09-29T18:26:17Z)
• Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning [34.6490677122246]
  We show that current Medical Vision-Language Models (Med-VLMs) exhibit concerning fragility in Medical Visual Question Answering.<n>We propose Consistency and Contrastive Learning (CCL), which integrates knowledge-anchored consistency learning and bias-aware contrastive learning.<n>CCL achieves SOTA performance on three popular VQA benchmarks and notably improves answer consistency by 50% on the challenging RoMed test set.
  arXiv  Detail & Related papers  (2025-08-26T05:21:19Z)
• Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation [108.13261761812517]
  We introduce FRANQ (Faithfulness-based Retrieval Augmented UNcertainty Quantification), a novel method for hallucination detection in RAG outputs.<n>We present a new long-form Question Answering (QA) dataset annotated for both factuality and faithfulness.
  arXiv  Detail & Related papers  (2025-05-27T11:56:59Z)
• Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering [42.116697933322875]
  Multimodal large language models (MLLMs) have demonstrated significant potential in medical Visual Question Answering (VQA)<n>They remain prone to hallucinations-incorrect responses that contradict input images, posing substantial risks in clinical decision-making.<n>Current hallucination detection methods, especially semantic entropy (SE), have demonstrated promising hallucination detection capacity for LLMs.<n>We propose Vision Amplified Semantic Entropy (VASE), which incorporates weak image transformations and amplifies the impact of visual input.
  arXiv  Detail & Related papers  (2025-03-26T12:45:34Z)
• VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation [18.873512856021357]
  We introduce VL-Uncertainty, the first uncertainty-based framework for detecting hallucinations in large vision-language models.<n>We measure uncertainty by analyzing the prediction variance across semantically equivalent but perturbed prompts.<n>When LVLMs are highly confident, they provide consistent responses to semantically equivalent queries.<n>But, when uncertain, the responses of the target LVLM become more random.
  arXiv  Detail & Related papers  (2024-11-18T04:06:04Z)
• To Believe or Not to Believe Your LLM [51.2579827761899]
  We explore uncertainty quantification in large language models (LLMs) We derive an information-theoretic metric that allows to reliably detect when only epistemic uncertainty is large. We conduct a series of experiments which demonstrate the advantage of our formulation.
  arXiv  Detail & Related papers  (2024-06-04T17:58:18Z)
• Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs [52.497823009176074]
  Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations.<n>We introduce Visual Description Grounded Decoding (VDGD), a training-free method designed to enhance visual perception and improve reasoning capabilities in LVLMs.
  arXiv  Detail & Related papers  (2024-05-24T16:21:59Z)
• KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking [55.2155025063668]
  KnowHalu is a novel approach for detecting hallucinations in text generated by large language models (LLMs) It uses step-wise reasoning, multi-formulation query, multi-form knowledge for factual checking, and fusion-based detection mechanism. Our evaluations demonstrate that KnowHalu significantly outperforms SOTA baselines in detecting hallucinations across diverse tasks.
  arXiv  Detail & Related papers  (2024-04-03T02:52:07Z)
• Towards Mitigating Hallucination in Large Language Models via Self-Reflection [63.2543947174318]
  Large language models (LLMs) have shown promise for generative and knowledge-intensive tasks including question-answering (QA) tasks. This paper analyses the phenomenon of hallucination in medical generative QA systems using widely adopted LLMs and datasets.
  arXiv  Detail & Related papers  (2023-10-10T03:05:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.