MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis (2026.acl-long)
Copied to clipboard
| Challenge: | Existing medical benchmarks fail to detect the Einstellung Effect in clinical diagnosis . Existing models exhibit the Einstellung effect, relying on statistical shortcuts rather than logical reasoning. |
| Approach: | They propose a counterfactual benchmark that uses statistical shortcuts to diagnose patients . they propose CGME-based system that iteratively refines reasoning paths . |
| Outcome: | The proposed model achieves high baseline accuracy but severe bias trap rates . iteratively refines reasoning paths in an exemplar base and consolidates disease-specific knowledge into illness graphs. |
Similar Papers
From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations (2025.emnlp-main)
Copied to clipboard
Benlu Wang, Iris Xia, Yifan Zhang, Junda Wang, null Feiyun Ouyang, Shuo Han, Arman Cohan, Hong Yu, Zonghai Yao
| Challenge: | Existing benchmarks assess only the final answer with a wide numerical tolerance, overlooking systematic reasoning failures and potentially causing serious clinical misjudgments. |
| Approach: | They propose a new step-by-step evaluation pipeline that assesses formula selection, entity extraction, and arithmetic computation. |
| Outcome: | The proposed method improves the accuracy of large language models on medical benchmarks from 16.35% to 53.19%. |
MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
Boqi Chen, Xudong Liu, Jiachuan Peng, Marianne Frey-Marti, Kyle Lam, Bang Zheng, Lin Li, Jianing Qiu
| Challenge: | Existing benchmarks for multimodal large language models do not capture real-world clinical complexity. |
| Approach: | They evaluate multilingual, multimodal multimodal models of clinical cases with up to 7 distinct visual clinical evidence types per case. |
| Outcome: | The proposed model outperforms human models on differential diagnosis (DDx) generation and final diagnosis (FDx) selection. |
Benchmarking LLMs on Authentic Cases from Medical Journals (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing medical benchmarks suffer from performance saturation due to medical exam questions. |
| Approach: | They evaluate the performance of over 20 open-source and proprietary large language models and benchmark them against human medical experts. |
| Outcome: | The new benchmark is based on authentic clinical cases sourced from medical journals and implements rigorous human review process to ensure the quality and reliability of the benchmark. |
Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are proving significant potential in healthcare, prompting numerous benchmarks to evaluate their capabilities. |
| Approach: | They propose a framework that deconstructs benchmark development into five stages from design to governance and provides a checklist of 46 medically-tailored criteria. |
| Outcome: | The framework deconstructs benchmark development into five stages from design to governance and provides a comprehensive checklist of 46 medically-tailored criteria. |
MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations test factual medical knowledge in isolation or assess patient-level reasoning without verifying correctness, leaving a critical gap. |
| Approach: | They propose a benchmark that links MIMIC-IV EHRs to a unified knowledge base built from UMLS and other biomedical vocabularies. |
| Outcome: | The proposed model improves by +16.4 macro-F1 points over the base model and eliminates truth inversion errors. |
MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings (2026.eacl-industry)
Copied to clipboard
Jean-Philippe Corbeil, Minseon Kim, Maxime Griot, Sheela Agarwal, Alessandro Sordoni, Francois Beaulieu, Paul Vozila
| Challenge: | Existing risk evaluations focused on general safety benchmarks, resulting in role-dependent vulnerabilities in real-world medical and clinical deployments. |
| Approach: | They propose a patient-oriented dataset called PatientSafetyBench that evaluates a variety of open- and closed-source LLMs. |
| Outcome: | The proposed benchmark examines medical risks from 466 open- and closed-source LLMs across 5 risk categories. |
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)
Copied to clipboard
Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current medical benchmarks have limitations in question design, data sources and evaluation methods. |
| Approach: | They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records . |
| Outcome: | The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios. |
C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to solve large language models address stereotypical and structural biases in isolation . however, prior paradigms address these in isolation, often at the expense of exacerbating the other . |
| Approach: | They propose a framework to tackle latent spurious feature correlations within input that drive erroneous reasoning shortcuts. |
| Outcome: | The proposed framework mitigates stereotypical and structural biases while preserving robust general reasoning capabilities. |
Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Current evaluations of large language models (LLMs) are limited in capturing key challenges of clinical diagnostic scenarios. |
| Approach: | They propose a dynamic benchmark for medical diagnostics that provides a stress test of diagnostic robustness. |
| Outcome: | The proposed model provides a stress test of diagnostic robustness and veracity, helpfulness and consistency. |
Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence (2026.findings-acl)
Copied to clipboard
Kaijie Mo, Siddhartha Venkatayogi, Chantal Shaib, Ramez Kouzy, Wei Xu, Byron C Wallace, Junyi Jessy Li
| Challenge: | Existing models are overwhelmingly accurate when presented with counterfactual medical evidence . prior work explored conflicts between context and LLM parametric knowledge in the general domain . |
| Approach: | They construct a counterfactual medical QA dataset that requires models to answer clinical comparison questions with evidence from randomized controlled trials. |
| Outcome: | The proposed model overemphasizes the latter, and the model overestimates the latter. |