mlsanityData to 7 Oct 2026

Retrieval Augmented Thought Process for Private Data Handling in Healthcare

arXiv 2402.07812 ↗First posted 12 Feb 2024cs.CL cs.AI cs.IRcited by 5

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

Large Language Models (LLMs) have demonstrated the strong potential to assist both clinicians and the general public with their extensive medical knowledge. However, their application in healthcare is constrained due to concerns about the privacy of data used in training, which prevents the integration of private and personal information because of security and ethical issues. Moreover, if their capabilities can be enhanced with information retrieval to access up-to-date knowledge, the current integration of LLMs with Information retrieval lacks robustness to imperfect retrieval, which can hinder their effectiveness and even reduce overall performance. In this work, we address this challenge by introducing the Retrieval-Augmented Thought Process (RATP). Given access to external knowledge, RATP formulates the thought generation of LLMs as a multiple-step decision process. To optimise such a thought process, RATP leverages Monte-Carlo Tree Search and learns a proxy reward function that permits cost-efficient inference. On a private dataset of electronic medical records, deliberately excluded from any LLM training set, RATP achieves 35% additional accuracy compared to in-context retrieval-augmented generation for the question-answering task.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 50 of its 84 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

50 of 84 references.

References · 50

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  10. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,140
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  12. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
38 more
  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  2. 2024Mixtral of Expertscited by 1,785
  3. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  5. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  6. 2023Teaching Large Language Models to Self-Debugcited by 963
  7. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  8. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  9. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  10. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  11. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  12. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  13. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  14. 2023LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 317
  15. 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
  16. 2022Generating Sequences by Learning to Self-Correctcited by 271
  17. 2023Language Modeling Is Compressioncited by 225
  18. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 218
  19. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
  20. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  21. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  22. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Modelscited by 167
  23. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  24. 2018emrQA: A Large Corpus for Question Answering on Electronic Medical Recordscited by 134
  25. 2023ProPILE: Probing Privacy Leakage in Large Language Modelscited by 127
  26. 2023Retrieval meets Long Context Large Language Modelscited by 114
  27. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 110
  28. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  29. 2024Large Language Models are Geographically Biasedcited by 91
  30. 2023Large AI Models in Health Informatics: Applications, Challenges, and the Futurecited by 61
  31. 2023Exploring Memorization in Fine-tuned Language Modelscited by 44
  32. 2023MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalitiescited by 38
  33. 2023Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Communitycited by 29
  34. 2023BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-inspired Materialscited by 29
  35. 2023Retrieval-Generation Synergy Augmented Large Language Modelscited by 26
  36. 2022DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queriescited by 17
  37. 2022You Are What You Write: Preserving Privacy in the Era of Large Language Modelscited by 11
  38. 2023Enhancing Small Medical Learners with Privacy-preserving Contextual Promptingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 2.

5 papers.

  1. 2024Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learningcited by 27
  2. 2026ProbeLLM: Automating Principled Diagnosis of LLM Failurescited by 7
  3. 2025Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Strongercited by 6
  4. 2026RAG over Thinking Traces Can Improve Reasoning Taskscited by 2
  5. 2024The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Datacited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval
  2. 2023MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering
  3. 2026A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
  4. 2026Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering
  5. 2025MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering
  6. 2025From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering
  7. 2025Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments
  8. 2025Med-R2: Crafting Trustworthy LLM Physicians via Retrieval and Reasoning of Evidence-Based Medicine