5arXiv cs.CL (Computation and Language)·
Closed-loop validation-repair achieves 99% schema compliance for clinical LLMs across healthcare standards
A new arXiv paper evaluates three open-source models (Qwen2.5 7B, Llama 3.1 8B, Gemma2 9B) on schema compliance with ICD-10, CPT, and HL7 FHIR standards across 960 clinical scenario-model pairs. Baseline compliance ranged from 85.9–91.6%, with 96% of failures being representation-level format violations rather than clinical reasoning errors. A closed-loop validation-repair framework raised overall compliance to 99.0%, with most errors resolving in one or two iterations, suggesting this system-level approach is a viable safeguard for healthcare EHR integration.
Related guides (2)
Related events (8)
ThReadMed-QA benchmark reveals frontier LLMs degrade sharply on medical misconception correction across multi-turn conversations
Researchers introduce ThReadMed-QA, a multi-turn medical dialogue dataset of 2,437 conversation threads (8,204 QA pairs) derived from real AskDocs patient interactions, designed to evaluate LLM ability to detect and correct embedded misconceptions over multiple turns. Evaluation of five LLMs using an LLM-as-a-Judge rubric finds that even frontier models like GPT-5 and Claude Haiku drop from ~85% misconception correction on initial questions to ~50% within two follow-up turns. Oracle analysis attributes much of this degradation to error propagation from prior model outputs rather than context length alone. The findings highlight a significant safety gap in current evaluation frameworks, which do not capture multi-turn conversational dynamics in medical settings.
MedQADE benchmark reveals LLM evaluators match physician agreement scores but lack clinical caution and show lineage bias
Researchers introduce MedQADE, a standardized open-response clinical benchmark for German comprising 3,800 items annotated by ten physicians and nine LLM evaluators. The top LLM evaluator (Gemini 3 Flash) reached statistical alignment near the physician inter-rater ceiling (κ=0.694 vs. κ=0.709), but automated evaluators showed near-zero clinical metacognition: unlike physicians, they never abstained regardless of item difficulty. The study also documents systematic lineage-dependent scoring bias, where models preferentially rate architectural siblings more favorably, independent of language.
Systematic evaluation of LLM prompt sensitivity in healthcare settings reveals safety risks
Researchers conduct a sensitivity analysis of both general-purpose and medical-specific LLMs using the MedMCQA benchmark, testing robustness to lexical and syntactic prompt perturbations. The study finds that even minor phrasing changes can alter clinical advice, and adversarial prompts can produce dangerous outputs such as incorrect dosages or omitted critical findings. Both general-purpose models (GPT-3.5, Llama 3) and domain-specific models (ClinicalBERT, BioLlama3, BioBERT) exhibit this fragility, with syntactic reordering and misleading contextual cues proving more destabilizing than simple paraphrasing.
Training framework reduces calibration error 60%+ in Medical VQA multimodal LLMs
A new arXiv preprint proposes a finetuning framework to improve verbalized uncertainty calibration in multimodal LLMs applied to Medical Visual Question Answering. The composite loss function combines Brier-style calibration, anchor regularization, contrastive image-text alignment, and KL-based stabilization, evaluated on MedGemma 4B IT and Qwen2-VL 7B Instruct across three medical VQA benchmarks. The method reduces calibration error by 60% or more and improves discrimination by 26% or more while preserving predictive accuracy, outperforming prompting-, sampling-, and training-based baselines.
CM-LRS: A capital markets reliability benchmark for LLM workflow outputs
Researchers introduce CM-LRS (Capital Markets LLM Reliability Score), a seven-dimension evaluation framework assessing LLM outputs at the workflow level rather than the question-answer layer, targeting regulated capital-markets use cases such as DCM/ECM term extraction, M&A comparables, and issuer profiling. The benchmark is demonstrated on five workflows using public SEC EDGAR and UK takeover filings, scoring four models across four LLM judges. Key findings: frontier closed-source models cluster tightly (Sonnet 4.6 = 4.31, Opus 4.7 = 4.30, GPT-5.5 = 4.09) while Llama 3.3 70B lags at 3.15, with the gap concentrated in retrieval and synthesis tasks rather than extraction. The work advances domain-specific evaluation methodology for high-stakes financial workflows where regulatory defensibility matters.
MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings
The paper introduces a pipeline for converting unstructured clinical text into HL7 FHIR R4 bundles, enabling evaluation of LLMs in realistic electronic health record settings. Applied to the MedCaseReasoning dataset, it produces MedCase-Structured, a synthetic benchmark achieving valid FHIR generation for 82.5% of cases. Key finding: LLMs show consistently lower diagnostic accuracy on structured FHIR inputs compared to plain text, underscoring the gap between standard benchmarks and real-world clinical deployment conditions.
LLM-guided MAP-Elites evolution improves medical decision pipelines at inference time
Researchers propose using LLM-guided MAP-Elites evolutionary search as an inference-time alternative to fine-tuning for adapting LLMs to clinical workflows, formulating triage, consultation, and image classification as evolutionary searches over executable artifacts. Across three medical settings, evolved programs substantially outperform manually designed baselines: triage accuracy improves from 77.3% to 87.1% and emergency recall from 0.60 to 0.97, with gains also shown on MIMIC-ESI, iCRAFTMD, and PneumoniaMNIST. The approach works across Llama-3, Qwen-3.5, and Gemma-4 backbones and produces interpretable program-level mechanisms rather than superficial prompt changes.
Sentence-Level Clinical Provenance Categorization for Multidisciplinary Hospital Summarization Using Fine-Tuned Llama-3
This pilot study presents a pipeline for categorizing sentence-level clinical provenance across multi-source hospital notes, targeting structured summarization in high-complexity settings like the NICU. The authors fine-tune Llama-3 8B and 70B models on MedSecId (MIMIC-III annotations), achieving Macro F1 above 92% in-domain. Cross-domain evaluation reveals a scale-dependent transfer effect: SFT substantially improves the 70B model (+7% Macro F1) but yields only marginal gains for the 8B model. A quantized fine-tuned 70B model outperforms its full-precision baseline while reducing compute, suggesting quantized adaptation is viable for structured clinical NLP tasks.