English(EN) Trick-or-Treat: Adversarial Evaluation of Multimodal Medical Reasoning with Synthetic Images

新基准揭示AI在医学图像分析中存在幻觉

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

研究人员开发了一个名为Trick-or-Treat的新基准，用于评估前沿AI模型的多模态医学推理能力，特别关注它们解读配对的胸部X光片和临床照片的能力。该基准使用合成临床照片创建对抗性场景，其中照片的发现故意与X光片的发现不匹配，从而揭示了当前模型中显著的幻觉行为。当呈现这些不匹配的配对时，前沿模型在45%到57.5%的时间里错误地识别了照片中的临床显著发现，通常会覆盖X光片的信息，以符合幻觉的照片诊断。 AI

影响强调了AI医学推理能力中潜在的风险，表明需要更强大的对抗性测试。

排序理由该集群包含一篇详细介绍用于评估AI模型的新基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 26 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍用于评估AI模型的新基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Oishi Banerjee, Eujin Lee, Sung Eun Kim, Alexandra N. Willauer, Christine Y. Zhou, Zhizhou Yang, Pranav Rajpurkar · 2026-11-05 05:00

不给糖就捣乱：利用合成图像对多模态医学推理进行对抗性评估

arXiv:2611.06631v1 Announce Type: cross Abstract: We used medical image synthesis to create a challenging multimodal evaluation framework that exposes hallucination behaviors in frontier models. Evaluating multimodal reasoning has historically been difficult because existing medi…

本文如何被排名

报道来源 [1]

不给糖就捣乱：利用合成图像对多模态医学推理进行对抗性评估

相关实体

相关话题