CLIMB: A Benchmark of Clinical Bias in Large Language Models

TL;DR

This paper introduces CLIMB, a comprehensive benchmark for evaluating intrinsic and extrinsic clinical bias in large language models, highlighting prevalent biases and emphasizing the need for mitigation in clinical applications.

Contribution

It presents the first systematic benchmark, including a novel metric AssocMAD and counterfactual evaluation methods, to assess clinical bias in LLMs.

Findings

Prevalent intrinsic and extrinsic biases found in popular LLMs.

AssocMAD effectively measures demographic disparities.

Counterfactual interventions reveal bias in clinical diagnosis tasks.

Abstract

Large language models (LLMs) are increasingly applied to clinical decision-making. However, their potential to exhibit bias poses significant risks to clinical equity. Currently, there is a lack of benchmarks that systematically evaluate such clinical bias in LLMs. While in downstream tasks, some biases of LLMs can be avoided such as by instructing the model to answer "I'm not sure...", the internal bias hidden within the model still lacks deep studies. We introduce CLIMB (shorthand for A Benchmark of Clinical Bias in Large Language Models), a pioneering comprehensive benchmark to evaluate both intrinsic (within LLMs) and extrinsic (on downstream tasks) bias in LLMs for clinical decision tasks. Notably, for intrinsic bias, we introduce a novel metric, AssocMAD, to assess the disparities of LLMs across multiple demographic groups. Additionally, we leverage counterfactual intervention to evaluate extrinsic bias in a task of clinical diagnosis prediction. Our experiments across popular and medically adapted LLMs, particularly from the Mistral and LLaMA families, unveil prevalent behaviors with both intrinsic and extrinsic bias. This work underscores the critical need to mitigate clinical bias and sets a new standard for future evaluations of LLMs' clinical bias.