A stakeholder-informed seven-criterion evaluation rubric spanning safety, reliability, and communication quality is developed and benchmarked 19 LLM judges across multiple implementation strategies, supporting LLM judges for scalable patient communication oversight while demonstrating the need for recalibration to patient-centered evaluation standards.
Abstract
LLMs are increasingly used to mediate patient communication, yet scalable evaluation of their safety, accuracy, and communication quality remains an open problem. LLM judges have emerged as automated evaluators, but whether they can holistically replicate human expert judgment is unvalidated. Informed consent for clinical trials presents a demanding case for such validation because it requires conveying complex information to lay audiences under ethical and safety constraints. We developed a stakeholder-informed seven-criterion evaluation rubric spanning safety, reliability, and communication quality. Clinician reference ratings showed strong interrater reliability across all criteria. We validated the rubric on the Informed CONsent Benchmark (ICON-Bench) and benchmarked 19 LLM judges across multiple implementation strategies. LLM judges achieved strong clinician agreement for safety screening and factual verification (Spearman {rho} > 0.80) but weaker agreement for communication quality ({rho} < 0.60). Safety-specialized guard models underperformed general-purpose models. Patient advocates rated communication quality lower than both clinicians and LLM judges. These findings support LLM judges for scalable patient communication oversight while demonstrating the need for recalibration to patient-centered evaluation standards.
Clinical documentation is essential to healthcare delivery but is timeconsuming, cognitively demanding, and prone to error. Large language models (LLMs) can generate draft notes, but may introduce hallucinations, unsupported inferences, or factual distortions that clinicians overlook. This study evaluated whether trans...
Abdus Samad· Proceedings of the Human Fac...· 0 citations
Large language models (LLMs) are increasingly used in primary care for documentation, patient communication, and clinical decision support. However, many clinicians are adopting these tools for patient care without structured training or a clear understanding of their limitations. LLM output may appear authoritative bu...
Christopher R. Stephenson, Christopher A. Aakre, I. Croghan et al.· Journal of Primary Care & Co...· 0 citations
Informed consent is delivered inconsistently, and the comprehension it should produce is often poor. We built ConsentAI, a conversational educational adjunct that guides patients through a surgeon-authored consent form and gates progression on demonstrated understanding. Before any patient-facing trial, we asked how su...
Anthony Abou Mrad, Jayanth S. Pratap, Aviona Conti et al.· npj Digital Surgery· 0 citations
Large language models (LLMs) deployed in mental-health contexts can be evaluated for safety failures, but the resulting judgments are often difficult to inspect or explain. Common approaches to improving safety rely on prompt engineering, LLM-as-a-Judge, and Constitutional AI. In this work, we describe a clinician-led...
Chenhan Lyu, Katherine E. Wislocki, S. Stoeckl et al.· 0 citations
Large language models are increasingly being used to evaluate clinical texts, a concept known as LLM-as-a-judge. However, most of the existing evidence focuses on English data and uses pooled agreement metrics that obscure clinically relevant failure modes. This study audited six open-weight models against expert judge...
T. Pakull, S. Warmer, K. Arzideh et al.· npj Digital Medicine· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.