mlsanityData to 14 Oct 2026

Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine

arXiv 2210.12777 ↗First posted 23 Oct 2022cs.CL cs.LGcited by 4

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

Abstract (arXiv)

Language models (LMs), including large language models (such as ChatGPT), have the potential to assist clinicians in generating various clinical notes. However, LMs are prone to produce ``hallucinations'', i.e., generated content that is not aligned with facts and knowledge. In this paper, we propose the Re3Writer method with retrieval-augmented generation and knowledge-grounded reasoning to enable LMs to generate faithful clinical texts. We demonstrate the effectiveness of our method in generating patient discharge instructions. It requires the LMs not to only understand the patients' long clinical documents, i.e., the health records during hospitalization, but also to generate critical instructional information provided both to carers and to the patient at the time of discharge. The proposed Re3Writer imitates the working patterns of physicians to first retrieve related working experience from historical instructions written by physicians, then reason related medical knowledge. Finally, it refines the retrieved working experience and reasoned medical knowledge to extract useful information, which is used to generate the discharge instructions for previously-unseen patients. Our experiments show that, using our method, the performance of five representative LMs can be substantially boosted across all metrics. Meanwhile, we show results from human evaluations to measure the effectiveness in terms of fluency, faithfulness, and comprehensiveness.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 35 references that are in the map. First posted on arXiv 23 Oct 2022.

Builds on

14 of 35 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2016Layer Normalizationcited by 5,669
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  8. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  9. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  10. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  11. 2015Gated Graph Sequence Neural Networkscited by 796
  12. 2019ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmissioncited by 493
2 more
  1. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 218
  2. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137

Built on by

Cited by year (2026 to 14 Oct)

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

4 papers.

  1. 2026When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoningcited by 5
  2. 2025CLIN-LLM: A Safety-Constrained Hybrid Framework for Clinical Diagnosis and Treatment Generationcited by 3
  3. 2026The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordinationcited by 3
  4. 2025Leveraging Evidence-Guided LLMs to Enhance Trustworthy Depression Diagnosiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Leaps Beyond the Seen: Reinforced Reasoning Augmented Generation for Clinical Notes
  2. 2025CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs
  3. 2025Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond
  4. 2024IgnitionInnovators at "Discharge Me!": Chain-of-Thought Instruction Finetuning Large Language Models for Discharge Summaries
  5. 2025Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations
  6. 2026Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction
  7. 2026Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies
  8. 2026ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation