@inproceedings{chen-etal-2026-medeinst,
    title = "{M}ed{E}inst: Benchmarking the Einstellung Effect in Medical {LLM}s through Counterfactual Differential Diagnosis",
    author = "Chen, Wenting  and
      Huang, Guolin  and
      Wang, Wenxuan  and
      Zhu, Zhongrui",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1847/",
    pages = "39778--39798",
    ISBN = "979-8-89176-390-6",
    abstract = "Despite achieving high accuracy on medical benchmarks, LLMs exhibit the Einstellung Effect in clinical diagnosis{---}relying on statistical shortcuts rather than patient-specific evidence, causing misdiagnosis in atypical cases. Existing benchmarks fail to detect this critical failure mode. We introduce MedEinst, a counterfactual benchmark with 5,383 paired clinical cases across 49 diseases. Each pair contains a control case and a ``trap'' case with altered discriminative evidence that flips the diagnosis. We measure susceptibility via Bias Trap Rate{---}probability of misdiagnosing traps despite correctly diagnosing controls. Evaluation shows frontier models achieve high baseline accuracy but severe bias trap rates. Thus, we propose ECR-Agent, aligning LLM reasoning with Evidence-Based Medicine via two components: (1) Dynamic Causal Inference (DCI) performs structured reasoning through dual-pathway perception, dynamic causal graph reasoning across three levels (association, intervention, counterfactual), and evidence audit for final diagnosis; (2) Critic-Driven Graph Memory Evolution (CGME) iteratively refines the system by storing validated reasoning paths in an exemplar base and consolidating disease-specific knowledge into evolving illness graphs. Source code is to be released."
}