Medical Large Language Model Benchmarks Should Prioritize Construct Validity

• URL: http://arxiv.org/abs/2503.10694v1
• Date: Wed, 12 Mar 2025 05:08:02 GMT
• Title: Medical Large Language Model Benchmarks Should Prioritize Construct Validity
• Authors: Ahmed Alaa, Thomas Hartvigsen, Niloufar Golchini, Shiladitya Dutta, Frances Dean, Inioluwa Deborah Raji, Travis Zack,
• Abstract summary: Medical large language models (LLMs) research often makes bold claims, from encoding clinical knowledge to reasoning like a physician.<n>But how do we separate real progress from a leaderboard flex?<n>We argue that medical LLM benchmarks should (and indeed can) be empirically evaluated for their construct validity.
• Score: 9.453444826672474
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical large language models (LLMs) research often makes bold claims, from encoding clinical knowledge to reasoning like a physician. These claims are usually backed by evaluation on competitive benchmarks; a tradition inherited from mainstream machine learning. But how do we separate real progress from a leaderboard flex? Medical LLM benchmarks, much like those in other fields, are arbitrarily constructed using medical licensing exam questions. For these benchmarks to truly measure progress, they must accurately capture the real-world tasks they aim to represent. In this position paper, we argue that medical LLM benchmarks should (and indeed can) be empirically evaluated for their construct validity. In the psychological testing literature, "construct validity" refers to the ability of a test to measure an underlying "construct", that is the actual conceptual target of evaluation. By drawing an analogy between LLM benchmarks and psychological tests, we explain how frameworks from this field can provide empirical foundations for validating benchmarks. To put these ideas into practice, we use real-world clinical data in proof-of-concept experiments to evaluate popular medical LLM benchmarks and report significant gaps in their construct validity. Finally, we outline a vision for a new ecosystem of medical LLM evaluation centered around the creation of valid benchmarks.

Related papers

• Automating Expert-Level Medical Reasoning Evaluation of Large Language Models [26.702477426812333]
  We introduce MedThink-Bench, a benchmark for rigorous, explainable, and scalable assessment of large language models' medical reasoning.<n>We also propose LLM-w-Ref, a novel evaluation framework that leverages fine-grained rationales and LLM-as-a-Judge mechanisms.<n>Overall, MedThink-Bench offers a foundational tool for evaluating LLMs' medical reasoning, advancing their safe and responsible deployment in clinical practice.
  arXiv  Detail & Related papers  (2025-07-10T17:58:26Z)
• LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation [38.02853540388593]
  evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error.<n>We present LLMEval-Med, a new benchmark covering five core medical areas, including 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.
  arXiv  Detail & Related papers  (2025-06-04T15:43:14Z)
• BRIDGE: Benchmarking Large Language Models for Understanding Real-world Clinical Practice Text [10.071956824618418]
  Large language models (LLMs) hold great promise for medical applications and are evolving rapidly. Most existing benchmarks rely on medical exam-style questions or PubMed-derived text. We present BRIDGE, a comprehensive benchmark comprising 87 tasks sourced from real-world clinical data sources across nine languages.
  arXiv  Detail & Related papers  (2025-04-28T04:13:18Z)
• Fact or Guesswork? Evaluating Large Language Model's Medical Knowledge with Structured One-Hop Judgment [108.55277188617035]
  Large language models (LLMs) have been widely adopted in various downstream task domains, but their ability to directly recall and apply factual medical knowledge remains under-explored. Most existing medical QA benchmarks assess complex reasoning or multi-hop inference, making it difficult to isolate LLMs' inherent medical knowledge from their reasoning capabilities. We introduce the Medical Knowledge Judgment, a dataset specifically designed to measure LLMs' one-hop factual medical knowledge.
  arXiv  Detail & Related papers  (2025-02-20T05:27:51Z)
• MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models [0.0]
  Medical Large Language Models (MLLMs) have demonstrated potential in healthcare applications.<n>Their propensity for hallucinations presents substantial risks to patient care.<n>This paper introduces MedHallBench, a comprehensive benchmark framework for evaluating and mitigating hallucinations in MLLMs.
  arXiv  Detail & Related papers  (2024-12-25T16:51:29Z)
• CliMedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models in Clinical Scenarios [50.032101237019205]
  CliMedBench is a comprehensive benchmark with 14 expert-guided core clinical scenarios. The reliability of this benchmark has been confirmed in several ways.
  arXiv  Detail & Related papers  (2024-10-04T15:15:36Z)
• MEDIC: Towards a Comprehensive Framework for Evaluating LLMs in Clinical Applications [2.838746648891565]
  We introduce MEDIC, a framework assessing Large Language Models (LLMs) across five critical dimensions of clinical competence. We apply MEDIC to evaluate LLMs on medical question-answering, safety, summarization, note generation, and other tasks. Results show performance disparities across model sizes, baseline vs medically finetuned models, and have implications on model selection for applications requiring specific model strengths.
  arXiv  Detail & Related papers  (2024-09-11T14:44:51Z)
• The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models [94.31327813151208]
  BiGGen Bench is a principled generation benchmark designed to thoroughly evaluate nine distinct capabilities of LMs across 77 diverse tasks. A key feature of the BiGGen Bench is its use of instance-specific evaluation criteria, closely mirroring the nuanced discernment of human evaluation.
  arXiv  Detail & Related papers  (2024-06-09T12:30:30Z)
• MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering [24.258546825446324]
  Large language models (LLM) have achieved impressive performance on medical question-answering benchmarks. We show how to use performance on a "MedFuzzed" benchmark, as well as individual successful attacks.
  arXiv  Detail & Related papers  (2024-06-03T18:15:56Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• Don't Make Your LLM an Evaluation Benchmark Cheater [142.24553056600627]
  Large language models(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs. We discuss the potential risk and impact of inappropriately using evaluation benchmarks and misleadingly interpreting the evaluation results.
  arXiv  Detail & Related papers  (2023-11-03T14:59:54Z)
• An Automatic Evaluation Framework for Multi-turn Medical Consultations Capabilities of Large Language Models [22.409334091186995]
  Large language models (LLMs) often suffer from hallucinations, leading to overly confident but incorrect judgments. This paper introduces an automated evaluation framework that assesses the practical capabilities of LLMs as virtual doctors during multi-turn consultations.
  arXiv  Detail & Related papers  (2023-09-05T09:24:48Z)
• CMB: A Comprehensive Medical Benchmark in Chinese [67.69800156990952]
  We propose a localized medical benchmark called CMB, a Comprehensive Medical Benchmark in Chinese. While traditional Chinese medicine is integral to this evaluation, it does not constitute its entirety. We have evaluated several prominent large-scale LLMs, including ChatGPT, GPT-4, dedicated Chinese LLMs, and LLMs specialized in the medical domain.
  arXiv  Detail & Related papers  (2023-08-17T07:51:23Z)
• Generating Benchmarks for Factuality Evaluation of Language Models [61.69950787311278]
  We propose FACTOR: Factual Assessment via Corpus TransfORmation, a scalable approach for evaluating LM factuality. FACTOR automatically transforms a factual corpus of interest into a benchmark evaluating an LM's propensity to generate true facts from the corpus vs. similar but incorrect statements. We show that: (i) our benchmark scores increase with model size and improve when the LM is augmented with retrieval; (ii) benchmark score and perplexity do not always agree on model ranking; (iii) when perplexity and benchmark score disagree, the latter better reflects factuality in open-ended generation.
  arXiv  Detail & Related papers  (2023-07-13T17:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.