CARE-Bench: Benchmarking Patient-Facing LLM Triage
Patient-facing medical LLMs and agents increasingly answer symptom questions before clinician contact, where the key safety question is what action the user should take next. We introduce CARE-Bench, a source-grounded benchmark that evaluates sequential patient-facing triage as a four-label per-turn current-action task. CARE-Bench contains 500 cases and 1,059 evaluated patient-disclosure prefixes reconstructed from medical dialogue, consultation, and follow-up-question sources. We evaluate 11 mo
Record details
Published: 4 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Healthcare · Agents & autonomy · Transparency
Retrieved: 5 August 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.
Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordination
arXiv · 5 August 2026
SHRIMP: Iterative Refinement of Robot Task Plans
arXiv cs.HC · 9 August 2026
Unmasking Toxic Mimicry in Medical Offline Reinforcement Learning for ICU Sepsis Management via Counterfactual Clinical Audits
arXiv cs.CY · 13 August 2026
Making Agent-Mediated Contributions Governable: A Project-Level Governance Manifest for Open-Source AI Collaboration
arXiv · 17 July 2026
Towards Autonomous and Auditable Medical Imaging Model Development
HuggingFace Daily Papers · 11 July 2026
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
arXiv · 29 June 2026
How to cite this record
ethics.ai (4 August 2026), “CARE-Bench: Benchmarking Patient-Facing LLM Triage,” evidence record 16556, https://ethics.ai/record/16556 (originally published by arXiv cs.AI).
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.