# Beyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs

arXiv: https://arxiv.org/abs/2609.32807 · HTML: https://mlsanity.com/paper/2609.32807/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Reading Race: AI Recognises Patient's Racial Identity In Medical Images](https://mlsanity.com/paper/2107.10356/) (2021)
- [MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models](https://mlsanity.com/paper/2403.03744/) (2024)

## Abstract (arXiv)

Clinical LLM evaluation often emphasizes answer accuracy; however, accuracy alone does not test counterfactual consistency or demographic robustness. We evaluated six LLMs on 150 MedQA USMLE questions using two automated perturbation tests to assess their performance. The counterfactual validity (CFV) test asked each model to make a minimal, plausible clinical change that would make a different answer correct. The demographic robustness test added six demographic prefixes to the same vignette and compared the answers and explanations with a no demographic baseline. Of the 900 CFV attempts, 228 (25.3 %) were valid and 672 were invalid. Across 5,400 demographic comparisons, 1,097 answers were changed (20.3%). Automated judging identified 3,128 stereotype evidence flags, including 1,932 in the broad Other category. MedGemma 27B achieved the highest accuracy (87.1%) and CFV (63.3%), lowest answer change rate (16.0%), and low mean Explanation Demographic Dissonance (EDD) score (0.169). However, its accuracy still exceeded its CFV, indicating that correct answers do not guarantee reliable performance on the counterfactual validity task. OpenBioLLM had the highest answer change rate and EDD, whereas GLM had the highest stereotype flag rate. These findings show that accuracy, CFV, answer stability, EDD, and stereotype evidence capture different evaluation aspects. Because all judgments were automated and no clinician validation was available, the results support safety screening but do not establish clinical deployability of the model.