MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection
Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a clinician-built synthetic benchmark and failure atlas that labels medical AI errors by severity (1--5) and safety gate type (missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, source support gap). The current public release (v0.2.1) contains 44 clinician-reviewed
Record details
Published: 16 July 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Healthcare
Retrieved: 18 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation
arXiv cs.HC · 16 July 2026
Knowledge-Guided Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Label-Conditioned Contrastive Alignment
arXiv cs.LG · 17 July 2026
NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis
arXiv cs.LG · 15 July 2026
Fine-Tuning, Retrieval-Augmented Generation, and Hybrid Large Language Models for Postoperative Decision Support: Comparative Analysis
JMIR (Journal of Medical Internet Research) · 14 July 2026
Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment
arXiv · 19 July 2026
Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment
arXiv · 19 July 2026
How to cite this record
ethics.ai (16 July 2026), “MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection,” evidence record 11346, https://ethics.ai/record/11346 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.