paper
LLM-Guided Evolution for Medical Decision Pipelines
paperactiveprovisional
llm-guided-evolution-for-medical-decision-pipelines-95e1e12d·1 events·first seen 9d agoAliases: LLM-Guided Evolution for Medical Decision Pipelines
Co-occurring entities
More like this (12)
LLM-augmented clinical NLP pipelineLLM-assisted theme discovery pipelineLLM-based code change labeling pipelineLLM-Guided Model PatchesMeasuring Epistemic Resilience of LLMs Under Misleading Medical ContextBidirectional Evolutionary SearchClinically Grounded Privacy Evaluation of Medical LMsOpen Medical-LLM LeaderboardTraining LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference OptimizationEvolution Strategieshuman-LLM collaborative annotationLLM inference
Recent events (1)
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.