Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine

• URL: http://arxiv.org/abs/2406.02394v2
• Date: Sat, 31 May 2025 11:21:22 GMT
• Title: Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine
• Authors: Maxime Griot, Jean Vanderdonckt, Demet Yuksel, Coralie Hemptinne,
• Abstract summary: Large Language Models (LLMs) demonstrate significant potential in the medical domain.<n>They are often evaluated using multiple-choice questions (MCQs) modeled on exams like the USMLE.<n>We created a fictional medical benchmark centered on an imaginary organ, the Glianorex, allowing us to separate memorized knowledge from reasoning ability.
• Score: 3.471944921180245
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) such as ChatGPT demonstrate significant potential in the medical domain and are often evaluated using multiple-choice questions (MCQs) modeled on exams like the USMLE. However, such benchmarks may overestimate true clinical understanding by rewarding pattern recognition and test-taking heuristics. To investigate this, we created a fictional medical benchmark centered on an imaginary organ, the Glianorex, allowing us to separate memorized knowledge from reasoning ability. We generated textbooks and MCQs in English and French using leading LLMs, then evaluated proprietary, open-source, and domain-specific models in a zero-shot setting. Despite the fictional content, models achieved an average score of 64%, while physicians scored only 27%. Fine-tuned medical models outperformed base models in English but not in French. Ablation and interpretability analyses revealed that models frequently relied on shallow cues, test-taking strategies, and hallucinated reasoning to identify the correct choice. These results suggest that standard MCQ-based evaluations may not effectively measure clinical reasoning and highlight the need for more robust, clinically meaningful assessment methods for LLMs.

Related papers

• Evaluating the performance and fragility of large language models on the self-assessment for neurological surgeons [0.7587293779231332]
  The Congress of Neurological Surgeons Self-Assessment for Neurological Surgeons ( CNS-SANS) questions are widely used by neurosurgical residents to prepare for written board examinations.<n>This study aims to assess the performance of state-of-the-art LLMs on neurosurgery board-like questions and to evaluate their robustness to the inclusion of distractor statements.<n>A comprehensive evaluation was conducted using 28 large language models.<n>These models were tested on 2,904 neurosurgery board examination questions derived from the CNS-SANS.
  arXiv  Detail & Related papers  (2025-05-29T14:27:14Z)
• AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation [55.2739790399209]
  We present AutoMedEval, an open-sourced automatic evaluation model with 13B parameters specifically engineered to measure the question-answering proficiency of medical LLMs.<n>The overarching objective of AutoMedEval is to assess the quality of responses produced by diverse models, aspiring to significantly reduce the dependence on human evaluation.
  arXiv  Detail & Related papers  (2025-05-17T07:44:54Z)
• MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports [49.00805568780791]
  We introduce MedCaseReasoning, the first open-access dataset for evaluating Large Language Models (LLMs) on their ability to align with clinician-authored diagnostic reasoning.<n>The dataset includes 14,489 diagnostic question-and-answer cases, each paired with detailed reasoning statements.<n>We evaluate state-of-the-art reasoning LLMs on MedCaseReasoning and find significant shortcomings in their diagnoses and reasoning.
  arXiv  Detail & Related papers  (2025-05-16T22:34:36Z)
• Disentangling Reasoning and Knowledge in Medical Large Language Models [23.401484250342158]
  Medical reasoning in large language models aims to emulate clinicians' diagnostic thinking.<n>Current benchmarks such as MedQA-USMLE, MedMCQA, and PubMedQA often mix reasoning with factual recall.<n>We evaluate biomedical models (HuatuoGPT-o1, MedReason, m1) and general-domain models (DeepSeek-R1, o4-mini, Qwen3)<n>We train BioMed-R1 using fine-tuning and reinforcement learning on reasoning-heavy examples.
  arXiv  Detail & Related papers  (2025-05-16T17:16:27Z)
• It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education [0.7771252627207672]
  The performance of Large Language Models (LLMs) on multiple-choice question (MCQ) benchmarks is frequently cited as proof of their medical capabilities. We created a novel benchmark of free-response questions with paired MCQs (FreeMedQA) Using this benchmark, we evaluated three state-of-the-art LLMs (GPT-4o, GPT-3.5, and LLama-3-70B-instruct) and found an average absolute deterioration of 39.43% in performance on free-response questions.
  arXiv  Detail & Related papers  (2025-03-13T19:42:04Z)
• Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English [66.97110551643722]
  We investigate dialectal disparities in Large Language Models (LLMs) reasoning tasks. We find that LLMs produce less accurate responses and simpler reasoning chains and explanations for AAE inputs. These findings highlight systematic differences in how LLMs process and reason about different language varieties.
  arXiv  Detail & Related papers  (2025-03-06T05:15:34Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions. We propose a novel approach utilizing structured medical reasoning. Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• 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)
• 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)
• Can Large Language Models Logically Predict Myocardial Infarction? Evaluation based on UK Biobank Cohort [10.66506859118868]
  Large language models (LLMs) have seen extraordinary advances with applications in clinical decision support. This study aims to evaluate quantitatively whether universal state-of-the-art LLMs can predict the incidence risk of myocardial infarction (MI) with logical inference.
  arXiv  Detail & Related papers  (2024-09-22T14:57:31Z)
• MedExQA: Medical Question Answering Benchmark with Multiple Explanations [2.2246416434538308]
  This paper introduces MedExQA, a novel benchmark in medical question-answering to evaluate large language models' (LLMs) understanding of medical knowledge through explanations. By constructing datasets across five distinct medical specialties, we address a major gap in current medical QA benchmarks. Our work highlights the importance of explainability in medical LLMs, proposes an effective methodology for evaluating models beyond classification accuracy, and sheds light on one specific domain, speech language pathology.
  arXiv  Detail & Related papers  (2024-06-10T14:47:04Z)
• Performance of large language models in numerical vs. semantic medical knowledge: Benchmarking on evidence-based Q&As [1.0034156461900003]
  Large language models (LLMs) show promising results in many aspects of language-based clinical practice. We used a comprehensive medical knowledge graph (encompassed data from more than 50,00 peer-reviewed articles) and created the "EBMQA" We benchmarked this dataset using more than 24,500 questions on two state-of-the-art LLMs: Chat-GPT4 and Claude3-Opus. We found that both LLMs excelled more in semantic than numerical QAs, with Claude3 surpassing GPT4 in numerical QAs.
  arXiv  Detail & Related papers  (2024-06-06T08:41:46Z)
• MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering [8.110978727364397]
  Large Language Models (LLMs) have the potential of facilitating the development of Artificial Intelligence technology. This paper presents MedExpQA, the first multilingual benchmark based on medical exams to evaluate LLMs in Medical Question Answering.
  arXiv  Detail & Related papers  (2024-04-08T15:03:57Z)
• Large Language Model Distilling Medication Recommendation Model [61.89754499292561]
  We harness the powerful semantic comprehension and input-agnostic characteristics of Large Language Models (LLMs) Our research aims to transform existing medication recommendation methodologies using LLMs. To mitigate this, we have developed a feature-level knowledge distillation technique, which transfers the LLM's proficiency to a more compact model.
  arXiv  Detail & Related papers  (2024-02-05T08:25:22Z)
• LLaMA Beyond English: An Empirical Study on Language Capability Transfer [49.298360366468934]
  We focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. We analyze the impact of key factors such as vocabulary extension, further pretraining, and instruction tuning on transfer. We employ four widely used standardized testing benchmarks: C-Eval, MMLU, AGI-Eval, and GAOKAO-Bench.
  arXiv  Detail & Related papers  (2024-01-02T06:29:02Z)
• Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages [51.301942056881146]
  We investigate how large language models (LLMs) function as rerankers in cross-lingual information retrieval systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) We examine cross-lingual reranking with queries in English and passages in the African languages.
  arXiv  Detail & Related papers  (2023-12-26T18:38:54Z)
• MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models [56.36916128631784]
  We introduce MedBench, a comprehensive benchmark for the Chinese medical domain. This benchmark is composed of four key components: the Chinese Medical Licensing Examination, the Resident Standardization Training Examination, and real-world clinic cases. We perform extensive experiments and conduct an in-depth analysis from diverse perspectives, which culminate in the following findings.
  arXiv  Detail & Related papers  (2023-12-20T07:01:49Z)
• A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology [0.6213359027997152]
  The study was conducted to evaluate the ability of LLM models to provide correct answers to nephSAP multiple-choice questions. The findings of this study potentially have significant implications for the future medical training and patient care.
  arXiv  Detail & Related papers  (2023-08-09T05:01:28Z)
• Evaluating Large Language Models for Radiology Natural Language Processing [68.98847776913381]
  The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP) This study seeks to bridge this gap by critically evaluating thirty two LLMs in interpreting radiology reports.
  arXiv  Detail & Related papers  (2023-07-25T17:57:18Z)
• Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset [31.047827145874844]
  We introduce CMExam, sourced from the Chinese National Medical Licensing Examination. CMExam consists of 60K+ multiple-choice questions for standardized and objective evaluations, as well as solution explanations for model reasoning evaluation in an open-ended manner. For in-depth analyses of LLMs, we invited medical professionals to label five additional question-wise annotations, including disease groups, clinical departments, medical disciplines, areas of competency, and question difficulty levels.
  arXiv  Detail & Related papers  (2023-06-05T16:48:41Z)
• Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundaries [48.48630043740588]
  Large Language Models (LLMs) such as ChatGPT and Med-PaLM have excelled in various medical question-answering tasks. We develop a novel in-context learning framework to enhance their performance.
  arXiv  Detail & Related papers  (2023-05-17T12:31:26Z)
• Large Language Models Encode Clinical Knowledge [21.630872464930587]
  Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning.
  arXiv  Detail & Related papers  (2022-12-26T14:28:24Z)

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.