arXiv:2609.24516v1 Announce Type: new Abstract: In recent years, large language models (LLMs) have emerged as a popular alternative for evaluation. Often referred to as LLMs as judges (LLJs), these s...
The study evaluates AI-generated summaries for cancer patients using a dual assessment framework that includes human experts and LLM-as-a-judge. Human domain experts—oncology clinicians and patient-facing care staff—assess summary quality on accuracy, clinical relevance, and readability. The research identifies limitations such as omissions and minor inaccuracies, which are then used to iteratively refine prompts, grounding, and safety guardrails.
arXiv:2609.37788v1 Announce Type: cross Abstract: Rubrics support the structured evaluation of language models. We propose a rubric for assessing expressed clinical reasoning in model responses, draw...
arXiv:2409. 07314v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) achieve superhuman performance on standardized medical licensing exams, these static benchmarks have become saturated and increasingly disconnected from the functional requirements of clinical workflows.
The study introduces Safety-Focused Evaluation of Scaling (SaFE-Scale) and applies it to RadSaFE-200, a 200-question radiology benchmark with clinician-defined evidence and safety labels. Thirty-four local large language models were tested under six deployment conditions, showing that providing clean clinician-written evidence significantly improved accuracy and reduced high-risk errors and dangerous overconfidence. The results indicate that safety in clinical LLMs depends more on deployment choices than on model size or inference-time compute.
arXiv:2607. 09932v1 Announce Type: cross Abstract: Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context.
The paper introduces a retrieval‑augmented multi‑agent framework that automatically generates instance‑specific evaluation rubrics for medical language models. By retrieving authoritative medical evidence, decomposing it into atomic facts, and combining these with user interaction constraints, the system produces fine‑grained criteria that outperform GPT‑4o on HealthBench and LLMEval‑Med. The generated rubrics also guide response refinement, improving medical LLM output quality by 9.2%.
arXiv:2606. 19183v1 Announce Type: cross Abstract: Large language models (LLMs) can make clinical decision support more accessible by interpreting free-text documentation, but their direct use as diagnostic engines is limited by sensitivity to prompts, information order, and plausible but incorrect outputs.
arXiv:2604.26766v2 Announce Type: replace-cross Abstract: Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly varia...
MTDiag is a newly released multi-turn diagnostic dialogue dataset designed to evaluate large language models (LLMs) in clinically meaningful ways. It is built from DDXPlus, MIMIC-IV, and AJCR case reports, covering both common emergency department presentations and rare conditions, and normalizes cases into a canonical schema using UMLS concept identifiers and ICD-10 codes. The dataset includes a UserLM‑8B utterance‑generation pipeline and physician‑validated natural‑language utterances, and introduces clinical knowledge‑grounded metrics that go beyond simple diagnostic accuracy for multi‑turn differential diagnosis tasks.
arXiv:2607. 24754v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to provide mental health support, requiring reliable evaluation of safety, empathy, and therapeutic appropriateness.
arXiv:2606. 00027v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed across healthcare, yet existing benchmarks fail to capture model behavior under adversarial or ethically complex conditions common in clinical practice.