同意还是正确？医学视觉-语言模型中的 grounding 与谄媚权衡
To Agree or To Be Right? The Grounding-Sycophancy Tradeoff in Medical Vision-Language Models
AI总结：
研究评估了六种医学视觉问答模型，揭示了 grounding 与谄媚之间的权衡关系，并提出三种新指标以评估模型的可靠性与安全性。
摘要：
视觉-语言模型（VLMs）适应医疗领域后在视觉问答基准上表现出色，但其对两种关键失败模式（幻觉和谄媚）的鲁棒性仍不明确，尤其在组合情况下。我们评估了六个VLMs（三种通用型，三种医疗专家型）在三个医疗VQA数据集上的表现，揭示了grounding与sycophancy之间的权衡：hallucination倾向最低的模型最谄媚，而最抗压的模型比所有医疗专家型模型更易产生幻觉。为表征这种权衡，我们提出了三个指标：L-VASE，一种logit空间重述的VASE，避免了其双归一化；CCS，一种经过置信度校准的谄媚评分，惩罚高置信度的妥协；以及临床安全指数（CSI），一种统一的安全指数，通过几何平均结合grounding、自主性和校准。在1151个测试案例中，没有模型达到CSI超过0.35，表明没有评估的7-8B参数VLM同时具备良好grounding和对社会压力的鲁棒性。我们的发现表明，在这些模型用于临床使用之前，必须联合评估这两种属性。代码可在https://github.com/UTSA-VIRLab/AgreeOrRight获取。
英文摘要：
Vision-language models (VLMs) adapted to the medical domain have shown strong performance on visual question answering benchmarks, yet their robustness against two critical failure modes, hallucination and sycophancy, remains poorly understood, particularly in combination. We evaluate six VLMs (three general-purpose, three medical-specialist) on three medical VQA datasets and uncover a grounding-sycophancy tradeoff: models with the lowest hallucination propensity are the most sycophantic, while the most pressure-resistant model hallucinates more than all medical-specialist models. To characterize this tradeoff, we propose three metrics: L-VASE, a logit-space reformulation of VASE that avoids its double-normalization; CCS, a confidence-calibrated sycophancy score that penalizes high-confidence capitulation; and Clinical Safety Index (CSI), a unified safety index that combines grounding, autonomy, and calibration via a geometric mean. Across 1,151 test cases, no model achieves a CSI above 0.35, indicating that none of the evaluated 7-8B parameter VLMs is simultaneously well-grounded and robust to social pressure. Our findings suggest that joint evaluation of both properties is necessary before these models can be considered for clinical use. Code is available at https://github.com/UTSA-VIRLab/AgreeOrRight
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
