mlsanityData to 14 Oct 2026

BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection

arXiv 2604.10389 ↗First posted 12 Apr 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → Medical and biomedical RAG

also in 1 more
Abstract (arXiv)

Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses; when the experts disagree, a structured counter-argumentation round and cross-source adjudication resolve the conflict, followed by a cascading safety layer that filters common false-positive patterns. We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families. Experimental results show that BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines. Further analyses across six backbone models and two prompting strategies confirm that retrieval augmentation and structured debate are complementary, and that the framework benefits most from models with sufficient instruction-following and clinical language understanding.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 39 of its 60 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

39 of 60 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Benchmarking Retrieval-Augmented Generation for Medicine20 Feb

Other references · 38

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2024GPT-4o System Cardcited by 4,588
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  8. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  10. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  11. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  12. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
26 more
  1. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  2. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  3. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMscited by 114
  4. 2024On scalable oversight with weak LLMs judging strong LLMscited by 99
  5. 2023Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debatecited by 97
  6. 2025Gemini Embedding: Generalizable Embeddings from Geminicited by 94
  7. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 89
  8. 2024MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notescited by 80
  9. 2024RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generationcited by 61
  10. 2024R2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoningcited by 43
  11. 2024RAG-Fusion: a New Take on Retrieval-Augmented Generationcited by 42
  12. 2025MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Modelscited by 34
  13. 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detectioncited by 23
  14. 2024Comparing Two Model Designs for Clinical Note Generation; Is an LLM a Useful Evaluator of Consistency?cited by 20
  15. 2024Retrieval-Augmented Generation with Estimation of Source Reliabilitycited by 19
  16. 2025SLOT: Structuring the Output of Large Language Modelscited by 18
  17. 2023Selective Generation for Controllable Language Modelscited by 15
  18. 2024SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarizationcited by 12
  19. 2025Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluationcited by 10
  20. 2024Harnessing Large Language Models as Post-hoc Correctorscited by 7
  21. 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalcited by 5
  22. 2025Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semanticscited by 5
  23. 2025From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notescited by 4
  24. 2025TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domaincited by 4
  25. 2023BM25 Query Augmentation Learned End-to-Endcited by 3
  26. 2025A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectivescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
  2. 2026Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation
  3. 2024IryoNLP at MEDIQA-CORR 2024: Tackling the Medical Error Detection & Correction Task On the Shoulders of Medical Agents
  4. 2025Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation
  5. 2025A Systematic Analysis of Large Language Models with RAG-enabled Dynamic Prompting for Medical Error Detection and Correction
  6. 2025MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts
  7. 2026ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory
  8. 2026GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models