# Rethinking Evidence Hierarchies in Medical Language Benchmarks: A Critical Evaluation of HealthBench

arXiv: https://arxiv.org/abs/2508.00081 · HTML: https://mlsanity.com/paper/2508.00081/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 11 of its 39 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 11 of 11)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering](https://mlsanity.com/paper/2203.14371/) (2022)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [Can large language models reason about medical questions?](https://mlsanity.com/paper/2207.08143/) (2022)
- [MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs](https://mlsanity.com/paper/2501.17399/) (2025)
- [Artificial Intelligence Index Report 2025](https://mlsanity.com/paper/2504.07139/) (2025)
- [AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset](https://mlsanity.com/paper/2411.15640/) (2024)
- [A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look](https://mlsanity.com/paper/2411.08275/) (2024)
- [Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias](https://mlsanity.com/paper/2405.15739/) (2024)
- [FairMedQA: Benchmarking Bias in Large Language Models for Medical Question Answering](https://mlsanity.com/paper/2505.19562/) (2025)

## Built on by (most cited first, 2 of 2)

- [Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health](https://mlsanity.com/paper/2511.17554/) (2025)
- [Decomposing Physician Disagreement in HealthBench](https://mlsanity.com/paper/2602.22758/) (2026)

## Abstract (arXiv)

HealthBench, a benchmark designed to measure the capabilities of AI systems for health better (Arora et al., 2025), has advanced medical language model evaluation through physician-crafted dialogues and transparent rubrics. However, its reliance on expert opinion, rather than high-tier clinical evidence, risks codifying regional biases and individual clinician idiosyncrasies, further compounded by potential biases in automated grading systems. These limitations are particularly magnified in low- and middle-income settings, where issues like sparse neglected tropical disease coverage and region-specific guideline mismatches are prevalent. The unique challenges of the African context, including data scarcity, inadequate infrastructure, and nascent regulatory frameworks, underscore the urgent need for more globally relevant and equitable benchmarks. To address these shortcomings, we propose anchoring reward functions in version-controlled Clinical Practice Guidelines (CPGs) that incorporate systematic reviews and GRADE evidence ratings. Our roadmap outlines "evidence-robust" reinforcement learning via rubric-to-guideline linkage, evidence-weighted scoring, and contextual override logic, complemented by a focus on ethical considerations and the integration of delayed outcome feedback. By re-grounding rewards in rigorously vetted CPGs, while preserving HealthBench's transparency and physician engagement, we aim to foster medical language models that are not only linguistically polished but also clinically trustworthy, ethically sound, and globally relevant.