# CARE-Bench: Benchmarking Patient-Facing LLM Triage

arXiv: https://arxiv.org/abs/2608.03731 · HTML: https://mlsanity.com/paper/2608.03731/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge](https://mlsanity.com/paper/2303.14070/) (2023)
- [MedDialog: Two Large-scale Medical Dialogue Datasets](https://mlsanity.com/paper/2004.03329/) (2020)
- [Follow-up Question Generation For Enhanced Patient-Provider Conversations](https://mlsanity.com/paper/2503.17509/) (2025)
- [How people use Copilot for Health](https://mlsanity.com/paper/2604.15331/) (2026)
- [Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries](https://mlsanity.com/paper/2605.15680/) (2026)

## Built on by (most cited first, 1 of 1)

- [How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs](https://mlsanity.com/paper/2610.18529/) (2026)

## Abstract (arXiv)

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 models on 269 held-out rounds under unprompted and minimally prompted open-ended protocols, using a fixed GPT-5.5 mapper to code each response into the four-label action space. Unprompted macro-F1 remains low, ranging from 31.2 to 50.4. Prompting improves 10 of 11 models, with prompted macro-F1 ranging from 46.9 to 63.4, but substantial threshold errors remain. Prompted models often recommend care before needed clarification is obtained; when the correct action was to ask for more information, only 33.5% of prompted outputs preserved the step. The persistence of these errors after prompting suggests that patient-facing triage is not a simple prompting problem and supports explicit evaluation of action timing before deployment.