Large language models now answer medical questions with expert-level performance. However, the context these systems act on can be misleading, and misleading context can corrupt a model's medical judgment. To understand how misleading context corrupts this judgment, we examine the model's susceptibility to the context, disclosure of it, mechanism of corrupted reasoning, and monitorability of the decision. On the medical reasoning subset of MedMisBench, a clinician-reviewed question-answering benchmark of 8,627 questions, we inject two types of misleading context cues, fabricated evidence and a bare assertion. We test three reasoning models, two that expose their full reasoning trace and one frontier model that exposes only its response. All three are more susceptible to the assertion than to the fabricated evidence, adopting the asserted answer 10 to 27 points more often. The misleading cues are disclosed in 81 to 98% of traces but only 7 to 90% of responses, and the assertion is disclosed less often than evidence based cues. Resampling from reasoning traces without disclosure shows the two cues corrupt reasoning differently, evidence entering early and accumulating while the assertion redirects the conclusion near its end. An LLM monitor catches 78% of corrupted decisions at 5% false positives when reading an open model's trace with guidance, against at most 32% from any response. The misleading context that models are most susceptible to is disclosed least, and was caught reliably only from an open reasoning trace, which frontier providers withhold.
Clinicians read chain-of-thought (CoT) rationales as evidence of medical reasoning, but whether the visible chain plays that role is rarely tested. General-domain CoT-faithfulness probes ignore clinical cost, and medical LLM evaluations treat the chain as a black box. We close this gap with a medical perturbation audit: a 30-operator battery edits both the chain and the question with clinically motivated operators (severity reversal, negation flip, demographic swap, evidence ablation), paired with a chain-update times answer-flip joint analysis that classifies each model by its failure mode. Applied to 14 LLMs on four medical QA benchmarks, three independent tests converge: the Chain-Decoupling Rate (CDR; chain does not register the edit and the answer does not flip) is 72.9% panel-wide on clinically meaningful destructive edits, chain corruption leaves accuracy unchanged, and removing CoT prompting does not reduce accuracy. Two board-certified clinicians re-annotate N=197 perturbed questions; 98.5% leave the gold defensible. The pattern holds across medical and reasoning fine-tuning and scale; on the closed-source tier, where the chain text is unavailable, the answer-side signals are consistent with the same decoupling. Our framework and CDR provide a reusable yardstick for auditing whether medical CoT is faithful or merely documentation.
Reinforcement learning with verifiable rewards has been especially effective in mathematics and coding, where answers can be checked automatically. Many open-ended medical questions lack comparably cheap outcome verifiers: responses may be partly correct, incomplete, or contain clinically consequential errors. Rubrics written or validated by physicians offer strong clinical grounding, but involving experts in every instance is costly. Model-generated rubrics make this supervision scalable. We introduce ConRub-Med to preserve useful distinctions as rubric feedback moves from construction to policy optimization. For each prompt, three heterogeneous language models propose atomic criteria independently; a separate model reviews them, retaining only criteria with semantic support from all three generators. Three-State scoring distinguishes correct coverage, missing information, and incorrect claims. Errors receive negative rather than zero credit. When every response in a complete Group Relative Policy Optimization (GRPO) group receives the same final reward, a pairwise judge provides sequence advantages only if both candidate orders agree, without changing the scalar rewards. Groups without ties use vanilla GRPO. In a blinded study matched by question, two medical experts rate panels from the full pipeline as more clinically relevant than panels produced by one generator. Across the evaluated open models, ConRub-Med ranks first on six of nine benchmarks and achieves the highest medical and generalization averages. Using the resulting rubric dataset of 5,166 prompts, it scores $38.98 \pm 1.04$ (mean $\pm$ SD) on HealthBench-Hard, compared with InfiMed-ORBIT's 33.60 with 8,000 samples and 37.30 with 28,000.
Uma Ranjan, Kunal Tilaganji, Aditya Koul +9cs.CV cs.SC
Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models to abstain when uncertain improves reliability but introduces a coverage accuracy tradeoff. We propose a two-stage framework for medical hypothesis verification in multiple-choice settings that manages this tradeoff through targeted ontology grounding, applied only when the model abstains. We show that abstention is not random but reflects genuine uncertainty, with abstained predictions associated with lower confidence. Across two frontier models (GPT-5.5, accessed via the Azure OpenAI API, and DeepSeek-R1), the proposed framework improves question-level accuracy by 9.6 percentage points (82.9% to 92.5%) and hypothesis-level accuracy by 4.2 percentage points (92.0% to 96.2%). Our experiments conducted on MedReason and MedQA show that abstention can be repurposed as a control signal for selective reasoning refinement, achieving knowledge-graph-level performance without explicit knowledge graph construction.
Maryam Tahermazandarani, Adnan Mahmood, Fahmida Islam +1cs.CL cs.AI cs.HC cs.LG
Large Language Models (LLMs) have achieved strong performance in medical question answering and clinical reasoning tasks. However, their reliability under uncertainty remains poorly understood which raises critical concerns for deployment in high-stakes clinical settings. In such environments, incorrect predictions are inherently risky, but confident incorrect predictions can be particularly harmful as they may mislead clinical decision-making. In this paper, we conduct a systematic behavioral analysis of LLMs under clinical information uncertainty. We propose an evaluation framework based on the MedMCQA dataset consisting of two complementary uncertainty settings. First, we introduce linguistic uncertainty cues through prompt modifications to simulate ambiguous clinical contexts. Second, we construct an answer removal setting, wherein the correct option is deliberately excluded mandating the model to recognize insufficient information and abstain. We analyze both model accuracy and confidence behavior using multiple calibration metrics including calibration gap, Expected Calibration Error (ECE), and Unsafe Confident Error Rate (UCER) across 500 medical questions. Our results reveal a consistent failure mode, i.e., although accuracy degrades under increasing uncertainty, model confidence remains misaligned with accuracy. This leads to a substantial increase in unsafe confident errors, indicating that model confidence remains largely insensitive to clinically meaningful information loss. Furthermore, we observe significant variation across models in their ability to abstain when the correct answer is unavailable, with some models persistently producing high confidence hallucinated answers. These findings expose critical limitations in the epistemic reliability of current LLMs and highlight the need for uncertainty aware evaluation methods prior to their deployment in clinical workflows.
Medical multiple-choice question answering requires parameter-efficient adaptation across heterogeneous knowledge domains and reasoning operations. A medication question, a diagnostic decision, a public-health item, and a nursing-action item may require different low-rank updates, while some recall items should preserve the base model's representation with only mild adapter intervention. We propose BiRG-LoRA, a single-adapter rank-gated LoRA method for medical question answering. BiRG-LoRA keeps one LoRA module per target layer but makes its rank dimension input-conditioned: for each question, a biaxial gate combines hidden semantic evidence with specialty/profession priors, clinical-operation priors, and their interaction to select a sparse top-$k$ subset of rank atoms. A scalar injection coefficient further controls the strength of the selected adapter update. Under a matched Qwen3-8B CMB-source protocol, BiRG-LoRA achieves the highest four-benchmark macro-average accuracy among trainable PEFT baselines and matched routing controls: 69.31% averaged over CMB, CMExam, MedQA, and MedMCQA. It improves over MoELoRA by 0.89 percentage points while using 28.1% fewer trainable parameters; a paired, benchmark-stratified bootstrap over final predictions gives a 95% confidence interval of [0.42, 1.37] for this macro-average gain. Basic controls show that BiRG-LoRA also improves over vanilla LoRA r16 and active-rank-matched LoRA r4 by 0.83 macro points, and an evaluation-time weak-axis perturbation check suggests that performance is not brittle to moderate tag noise. The results support a bounded claim: clinically structured rank allocation improves cross-benchmark medical QA under a matched single-seed protocol, while training-seed variance remains future work.
Maternal and newborn mortality remain among the highest in sub-Saharan Africa, where midwifery care is often delivered by nurses who lack midwifery training to international standards, and consulting authoritative guidance at the point of care is hard: the guidelines are long and connectivity is intermittent. We present MAM-AI, a medical question-answering assistant for nurse-midwives in Zanzibar that runs entirely on a commodity Android device: a question is embedded (EmbeddingGemma, 300M) and matched against a curated corpus of 87 guideline documents (63,650 passages), then answered with citations by a 4B int4 generator (Gemma 4 E4B), fully offline, with no query leaving the device. We evaluate the exact deployed configuration with a layered methodology -- retriever, generator under oracle context, end-to-end, and latency -- scored by LLM judges validated against physician rubrics. The evaluation relocates the hard problem. On-device retrieval is essentially solved: the 300M embedder ranks third of seven retrievers and rivals cloud systems, so the passages the system needs are usually found. The small generator is what remains in doubt: adding retrieved context does not improve its answers, and at 4B it cannot be both helpful and safe at once -- of two same-size candidates, the more helpful one commits genuine dangerous errors, so we deploy the other, which is about twice as faithful to its sources (as faithful as a frontier model), and recover its helpfulness with a redesigned prompt that cuts deflection from 33% to 3%. Corpus quality is decisive for the same reason: where the corpus holds the right passage the answer is specific and actionable, and where it does not it goes vague. MAM-AI is a thoroughly evaluated, open-source research prototype, not a fielded product; the system, knowledge base, benchmarks, and evaluation harness are released.
Medical question-answering benchmarks rarely cover the maternal, neonatal, child, and reproductive-health questions a nurse-midwife asks, and, to our knowledge, no public chunk-level relevance benchmark exists for maternal-health guideline retrieval. We release two benchmarks that fill these gaps. mamabench is a scope-filtered QA set of 25,949 items assembled from seven existing expert-authored sources across multiple-choice, short-answer, and rubric-graded tracks; to help users calibrate the LLM judge that scores the rubric track, we re-scope HealthBench's physician-labelled meta-evaluation to the domain. mamaretrieval pairs 3,185 clinical queries with graded (0-6) relevance labels over a 63,650-chunk maternal-health guideline corpus, using a decomposed rubric that distinguishes a chunk that answers a query from one merely on its topic. Three decisions shape both: assemble and filter expert sources rather than author questions, grade relevance rather than binarise it, and measure and disclose the limits of the labels -- scope-classifier agreement, a frontier-judge check, and a pooling-completeness audit -- rather than treat them as an oracle. A companion paper uses the benchmarks to evaluate a deployed on-device assistant; both are released openly for research.
Large language models (LLMs) have shown promising performance across a wide range of biomedical applications, including medical question answering (QA), yet they remain prone to hallucinations and outdated knowledge. Although retrieval-augmented generation (RAG) can alleviate this issue by incorporating external documents, there still exist two fundamental limitations. First, medical knowledge is often fragmented across documents, while most RAG methods rely on a single retrieval path, which makes it challenging to jointly preserve fine-grained semantic information and structured global associations. Second, static retrieval strategies are typically insufficient to support deep reasoning that is important in complex medical QA. In this paper, we present a dual-path retrieval framework with an iterative retrieval-reasoning mechanism termed "Hybrid-IR" for complex medical QA. The proposed Hybrid-IR integrates graph-based retrieval for exploration of structured knowledge and dense retrieval for fine-grained semantic matching. Moreover, the reasoning trajectory can be progressively refined through an iterative retrieve-reason loop. Experiments on three widely used medical QA benchmarks demonstrate the effectiveness of our Hybrid-IR.
Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Method: We designed a multi-agent peer-reviewed reasoning method in which multiple LLM agents independently generate chain-of-thought reasoning with candidate answers, then act as peer reviewers to evaluate each other's reasoning for factual correctness and logical soundness. The highest-rated reasoning chain is selected to produce the final answer. Experiments were conducted with five state-of-the-art LLMs (Llama-3.1-8B, Qwen2.5-7B, Phi-4, DeepSeek-LLM-7B, GPT-oss-20B) on three benchmark datasets: HeadQA, MedQA-USMLE, and PubMedQA. Performance was compared against single-model chain-of-thought reasoning and chain-of-thought-based majority voting. Results: Peer-reviewed reasoning consistently outperformed both baselines. The best model combination achieved an average accuracy of 0.820 across datasets, exceeding the strongest single model (0.777) and majority voting ensembles (up to 0.789). The method also scaled effectively with more participating models, while peer assessments reliably distinguished high- from low-quality reasoning chains. Conclusion: The proposed multi-agent peer-reviewed reasoning method enables LLMs to act as both solvers and evaluators, yielding superior performance in MedQA. By emphasizing reasoning quality rather than answer agreement alone, this approach improves accuracy, interpretability, and robustness, offering a promising direction for trustworthy biomedical AI systems.
Large language models (LLMs) are increasingly used for everyday health questions, including whether a user can safely take another dose of an over-the-counter (OTC) medication. Yet this common safety-relevant setting remains underexplored in existing medical QA evaluations, where correct answers require tracking dose timing, computing rolling 24-hour intake, following product-label constraints, and handling incomplete medication histories. We introduce DOSEBENCH, a focused benchmark of 81 curated OTC dosing scenarios focused on adult acetaminophen and ibuprofen use, with manually annotated gold references. We evaluate four LLMs across repeated runs using metrics for decision correctness, consistency, explanation verifiability, failure types, and confidence-related signals, resulting in 1,620 model responses. Our results show that models frequently struggle with rolling-window reasoning and ambiguity-sensitive cases and that stable or confident-looking responses can still violate dosing constraints. These findings suggest that OTC dosing QA provides a narrow yet practical testbed for evaluating temporal reasoning, constraint following, and safety-relevant uncertainty handling in medical QA.
Medical RAG systems in high-risk QA settings are often evaluated through a single answer-or-abstain decision, but mixed evidence may support one claim, require conditions for another, and contradict a third. We study claim-selective certification: each response is decomposed into verifiable claims, scored against retrieved evidence, and mapped by an intent-aware selector to {full, partial, conflict, abstain}. On the primary weak-label certificate protocol, whose real-source-only dev/test rows cover the naturally occurring non-abstain actions, the full system records UCCR=0.0000, PAU=1.0000, PAU Precision=0.9901, and action accuracy=0.9204 on dev (n=314), and UCCR=0.0000, PAU=0.9967, PAU Precision=0.9739, and action accuracy=0.8997 on test (n=319). UCCR measures unsupported-claim risk within the certificate definition, and a source-missing counterfactual slice evaluates abstain under empty evidence. Shortcut controls quantify the action-label prior explained by source and intent metadata, while source/evidence-novel slices characterize transfer boundaries. The resulting interface separates action-label prediction from evidence-linked claim selection under mixed evidence.
Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual content (tables, figures, structured layouts) of original document pages. We propose MED-VRAG, an iterative multimodal RAG framework that retrieves and reasons over PMC document page images instead of OCR'd text. The system pairs ColQwen2.5 patch-level page embeddings with a sharded MapReduce LLM filter, scaling to ~350K pages while keeping Stage-1 retrieval under 30 ms via an offline coarse-to-fine index (C=8 centroids per page, ANN over centroids, exact two-way scoring on the top-R shortlist). A vision-language model (VLM) then iteratively refines its query and accumulates evidence in a memory bank across up to 3 reasoning rounds, with a single iteration costing ~15.9 s and the full three-round pipeline ~47.8 s on 4xA100. Across four medical QA benchmarks (MedQA, MedMCQA, PubMedQA, MMLU-Med), MEDVRAG reaches 78.6% average accuracy. Under controlled comparison with the same Qwen2.5-VL-32B backbone, retrieval contributes a +5.8 point gain over the no-retrieval baseline; we also note a +1.8 point edge over MedRAG + GPT-4 (76.8%), with the caveat that this is a cross-paper rather than head-to-head comparison. Ablations isolate +1.0 from page-image vs text-chunk retrieval, +1.5 from iteration, and +1.0 from the memory bank.
Knowledge graphs (KGs) are increasingly used to support large lan guage model (LLM) reasoning, but standard triplet-based KGs treat each relation as globally valid. In many settings, whether a relation should count as evidence depends on the context. We therefore formulate triplet validity as a triplet-specific function of context and refer to this formulation as a Quantum Knowledge Graph (QKG). We instantiate QKG in medicine using a diabetes-centered PrimeKG subgraph, whose 68,651 context-sensitive relations are further annotated with patient-group-specific constraints. We evaluate it in a reasoner--validator pipeline for medical question answering on a KG-grounded subset of MedReason containing 2,788 questions. With Haiku-4.5 as both the Reasoner and the Validator, KG-backed validation significantly improves over a no-validator baseline ($+0.61$ pp), and QKG with context matching yields the largest gain, outperforming both KG validation without context matching ($+0.79$ pp) and the no-validator baseline ($+1.40$ pp; paired McNemar, all $p<0.05$). Under a stronger validator (Qwen-3.6-Plus), the raw QKG gain over the no-validator baseline grows from $+1.40$ pp to $+5.96$ pp; the context-matching gap is non-significant ($p=0.73$) on the raw set but becomes borderline significant ($p=0.05$) after adjustment for knowledge leakage and suspicious questions, consistent with a benchmark-gold ceiling rather than a QKG limitation. Taken together, the results support the view that the value of a KG in LLM-based clinical reasoning lies not merely in storing medically related facts, but in representing whether those facts are applicable to the specific patient context. For reproducibility and further research, we release the curated QKG datasets and source code.\footnote{https://github.com/HKAI-Sci/QKG}