The paper investigates how misleading context—specifically fabricated evidence and bare assertions—affects large language models’ medical question‑answering performance. Experiments on MedMisBench show that models are more prone to adopt answers based on assertions than fabricated evidence, and that these misleading cues are often disclosed in reasoning traces but rarely in final responses. A monitor that reads open reasoning traces can detect most corrupted decisions, whereas monitoring only responses is less effective.
arXiv:2608.01017v2 Announce Type: replace-cross Abstract: Large language models can answer a medical question correctly and still abandon that answer when a user pushes back. We study this failure as...
arXiv:2608. 09080v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks.
The study investigates how false content in training data can influence language models’ downstream decisions even without explicit triggers. By comparing models trained on misleading versus truthful documents in a controlled decision task and a real‑world bushfire case, the authors find a gap between factual answers and the decisions derived from them: correct facts do not always lead to correct decisions, and removing an injected number does not eliminate the misleading narrative. The research highlights that data poisoning can subtly alter model behavior beyond what is detectable through direct probing.
arXiv:2606. 07237v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question answering, diagnosis support, and report summarization.
arXiv:2607. 27304v1 Announce Type: new Abstract: Medical vision-language models (VLMs) generate chain-of-thought (CoT) reasoning before answering clinical questions, but whether this reasoning causally influences predictions remains unclear.
MedFabric is a new benchmark for detecting word‑level medical fabrications, comprising 646 fabricated statements each paired with a ground‑truth passage that shares the same LLM authorship and nearly identical wording. The study shows that current detectors perform poorly—expert clinicians achieve only 53.3% macro‑F1 and no detector family surpasses 60% without gold evidence—highlighting that detection hinges on evidence correctness rather than subtlety of fabrication. The authors demonstrate that a retrieval‑confidence gate can substantially improve performance, raising macro‑F1 from 61% to 74%.
The paper introduces three interpretable metrics—Explanation Stability Index (ESI), Causal Faithfulness Score (CFS), and Perturbation Stability Score (PSS)—to assess the faithfulness of large language models (LLMs) in clinical decision support. Evaluating six LLMs on 150 MedQA-USMLE questions, the study finds that only 23.3% of cited clinical concepts are causally necessary, and that correct answers often have lower CFS than incorrect ones, with answer consistency negatively predicting faithfulness. These findings suggest that accuracy, consistency, and consensus are incomplete safety signals for clinical decision-making support.
arXiv:2610.08585v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here we examine the impact of a...
arXiv:2601. 09853v3 Announce Type: replace-cross Abstract: Real-world health questions from patients often unintentionally embed false assumptions or premises.
arXiv:2610.00562v1 Announce Type: cross Abstract: Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate relevant evidence distributed across extended patient...
A medical vision-language model may analyze a given CT scan and correctly detect both kidneys in view. Continuing this conversation, if a user provides a prescription with an opposite direction, medic...
Large language models (LLMs) are increasingly relied upon to support ambient documentation and clinical reasoning. Here we examine the impact of a failure mode shared between these two applications by...