arXiv AI July 21, 2026 By Koyar Afrasyab

Judge-dependent safety gains and model-specific helpfulness costs of evidence-sufficiency prompting in clinical LLMs

arXiv:2607. 18086v1 Announce Type: new Abstract: Background: LLM judges increasingly score whether clinical language models give overconfident answers under incomplete evidence, yet whether a measured "safety gain" reflects real behavior change or the judge's calibration is unresolved.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 22

Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety

arXiv:2607. 18828v1 Announce Type: new Abstract: Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks.

By Koyar Afrasyab

llms multimodal benchmarks safety

arXiv Machine Learning

Jun 5

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures

arXiv:2604. 07709v4 Announce Type: replace-cross Abstract: A heavily safety-trained model will hand a physician the full, patient-followable benzodiazepine taper and refuse it to the patient who needs it, over identical clinical facts; the knowledge is present either way.

By David Gringras

llms benchmarks safety

arXiv AI

Aug 3

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support

arXiv:2607. 28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning.

By Shayndhan Sivanathan, Shravan Nageswaran, Mehdi Zadem, Ryaan Sultan, Nicolas von Mallinckrodt, Max Solovyev, Alexey Matyushkin, Sumon Sadhu, Gabriele C DeLuca, Sanjeeva Jeyaretna, James Hillis, Manoj Ramachandran, Prakash Jayakumar

llms agents safety

arXiv AI

Aug 5

Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety

arXiv:2608. 02617v1 Announce Type: cross Abstract: We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback from MOOVE (Massive Open Online Validation and Evaluation), a clinician-led platform collecting blinded pairwise preferences alongside multi-criterion rubric ratings.

By Fay Elhassan, David Sasu, Alexandra Kulinkina, Lars Henning Klein, Mary-Anne Hartley

llms safety

arXiv AI

1d ago

Large Language Models Show Metacognitive Sensitivity in Medical Reasoning

arXiv:2608. 14552v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated and used in medicine, but clinical usefulness depends on answer accuracy and whether confidence tracks evidence quality and uncertainty.

By Ahmad Nazzal

llms benchmarks

arXiv AI

Jul 1

Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support

arXiv:2606. 30887v1 Announce Type: cross Abstract: Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control signal rather than a passive metric.

By Mizanur Rahman, Abeer Badawi, Elahe Rahimi, Laleh Seyyed-Kalantari, Frank Rudzicz, Enamul Hoque, Elham Dolatabadi

llms agents nlp safety

Related stories

Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support

Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety

Large Language Models Show Metacognitive Sensitivity in Medical Reasoning

Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support