提出无需采样和外部模型的医学视觉问答幻觉检测方法
Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain
- 基于模型自身输出的置信度与视觉证据响应不一致来判断幻觉
- 在16个实验中13次达到最高AUC，平均比VASE高8点
- 适合临床部署，无需额外计算资源或调参
多模态大语言模型在医学视觉问答任务中展现出强大潜力，但易产生与图像矛盾的幻觉，临床风险高。现有检测方法如语义熵（SE）和视觉增强语义熵（VASE）需对每样本进行10至20次随机生成，并依赖外部自然语言推理模型进行语义聚类，计算成本高且难部署。我们观察到，幻觉回答在模型自身的对数概率中具有独特特征：词元级置信度不一致、对视觉证据敏感度弱。基于此，提出确定性幻觉检测方法Confidence-Evidence Bayesian Gain（CEBaG），无需随机采样、外部模型或任务特定超参数。CEBaG融合两种互补信号：词元级预测方差（捕捉置信度不一致性）和证据量（衡量图像对逐词预测的扰动程度）。在四个医学多模态大模型和三个VQA基准（共16个实验设置）上评估，CEBaG在13个设置中达到最高AUC，平均优于VASE 8 AUC点，且完全确定性和自包含。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。