mlsanityData to 14 Oct 2026

ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis

arXiv 2502.14614 ↗First posted 20 Feb 2025cs.CLcited by 0

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

Abstract (arXiv)

Retrieval-Augmented Large Language Models (LLMs), which integrate external knowledge, have shown remarkable performance in medical domains, including clinical diagnosis. However, existing RAG methods often struggle to tailor retrieval strategies to diagnostic difficulty and input sample informativeness. This limitation leads to excessive and often unnecessary retrieval, impairing computational efficiency and increasing the risk of introducing noise that can degrade diagnostic accuracy. To address this, we propose ICA-RAG (Information Completeness Guided Adaptive Retrieval-Augmented Generation), a novel framework for enhancing RAG reliability in disease diagnosis. ICA-RAG utilizes an adaptive control module to assess the necessity of retrieval based on the input's information completeness. By optimizing retrieval and incorporating knowledge filtering, ICA-RAG better aligns retrieval operations with clinical requirements. Experiments on three Chinese electronic medical record datasets demonstrate that ICA-RAG significantly outperforms baseline methods, highlighting its effectiveness in clinical diagnosis.

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 36 of its 47 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

36 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Rationale-Guided Retrieval Augmented Generation for Medical Question Answering1 Nov
  2. 2023Large Language Models with Retrieval-Augmented Generation for Zero-Shot Disease Phenotyping11 Dec

Other references · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  10. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  11. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  12. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
22 more
  1. 2023Active Retrieval Augmented Generationcited by 516
  2. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  3. 2019Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approachcited by 308
  4. 2022RealTime QA: What's the Answer Right Now?cited by 244
  5. 2024Capabilities of Gemini Models in Medicinecited by 237
  6. 2023CMB: A Comprehensive Medical Benchmark in Chinesecited by 115
  7. 2019StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understandingcited by 109
  8. 2023MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Modelscited by 73
  9. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
  10. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  11. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  12. 2021Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinesecited by 45
  13. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
  14. 2023How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advancescited by 33
  15. 2024ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real Worldcited by 28
  16. 2022Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrievalcited by 27
  17. 2024Guiding Clinical Reasoning with Large Language Models via Knowledge Seedscited by 19
  18. 2024LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generationcited by 17
  19. 2024medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRscited by 16
  20. 2024Enhancing Large Language Models for Clinical Decision Support by Incorporating Clinical Practice Guidelinescited by 11
  21. 2024Enhancing Healthcare LLM Trust with Atypical Presentations Recalibrationcited by 6
  22. 2023You Only Forward Once: Prediction and Rationalization in A Single Forward Passcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning
  2. 2025MIRA: A Novel Framework for Fusing Modalities in Medical RAG
  3. 2025RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
  4. 2026C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning
  5. 2025Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights
  6. 2025LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose Models
  7. 2026When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
  8. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems