# CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs

arXiv: https://arxiv.org/abs/2507.06715 · HTML: https://mlsanity.com/paper/2507.06715/

## 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 12 of its 30 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Placed in

- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [The Dynamic Embedded Topic Model](https://mlsanity.com/paper/1907.05545/) (2019)
- [Rationale-Guided Retrieval Augmented Generation for Medical Question Answering](https://mlsanity.com/paper/2411.00300/) (2024)
- [Intelligent Clinical Documentation: Harnessing Generative AI for Patient-Centric Clinical Note Generation](https://mlsanity.com/paper/2405.18346/) (2024)
- [A Survey on Medical Document Summarization](https://mlsanity.com/paper/2212.01669/) (2022)
- [GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning](https://mlsanity.com/paper/2305.05001/) (2023)
- [Toward Relieving Clinician Burden by Automatically Generating Progress Notes using Interim Hospital Data](https://mlsanity.com/paper/2410.12845/) (2024)

## Built on by (most cited first, 4 of 4)

- [When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation](https://mlsanity.com/paper/2605.24902/) (2026)
- [DENSE: Longitudinal Progress Note Generation with Temporal Modeling of Heterogeneous Clinical Notes Across Hospital Visits](https://mlsanity.com/paper/2507.14079/) (2025)
- [Clinical Document Metadata Extraction: A Scoping Review](https://mlsanity.com/paper/2601.09730/) (2025)
- [Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies](https://mlsanity.com/paper/2608.05993/) (2026)

## Abstract (arXiv)

Large language models (LLMs), including zero-shot and few-shot paradigms, have shown promising capabilities in clinical text generation. However, real-world applications face two key challenges: (1) patient data is highly unstructured, heterogeneous, and scattered across multiple note types and (2) clinical notes are often long and semantically dense, making naive prompting infeasible due to context length constraints and the risk of omitting clinically relevant information. We introduce CLI-RAG (Clinically Informed Retrieval-Augmented Generation), a domain-specific framework for structured and clinically grounded text generation using LLMs. It incorporates a novel hierarchical chunking strategy that respects clinical document structure and introduces a task-specific dual-stage retrieval mechanism. The global stage identifies relevant note types using evidence-based queries, while the local stage extracts high-value content within those notes creating relevance at both document and section levels. We apply the system to generate structured progress notes for individual hospital visits using 15 clinical note types from the MIMIC-III dataset. Experiments show that it preserves temporal and semantic alignment across visits, achieving an average alignment score of 87.7%, surpassing the 80.7% baseline from real clinician-authored notes. The generated outputs also demonstrate high consistency across LLMs, reinforcing deterministic behavior essential for reproducibility, reliability, and clinical trust.