# Disco-RAG: Discourse-Aware Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2601.04377 · HTML: https://mlsanity.com/paper/2601.04377/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 45 of its 83 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 30 of 45)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA](https://mlsanity.com/paper/2406.17419/) (2024)
- [MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models](https://mlsanity.com/paper/2410.13085/) (2024)
- [GRAG: Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2405.16506/) (2024)
- [StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization](https://mlsanity.com/paper/2410.08815/) (2024)
- [KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation](https://mlsanity.com/paper/2409.13731/) (2024)
- [Knowledge Graph-Guided Retrieval Augmented Generation](https://mlsanity.com/paper/2502.06864/) (2025)
- [KG-RAG: Bridging the Gap Between Knowledge and Creativity](https://mlsanity.com/paper/2405.12035/) (2024)
- [ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer](https://mlsanity.com/paper/2306.07799/) (2023)
- [MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.00332/) (2024)
- [Is Semantic Chunking Worth the Computational Cost?](https://mlsanity.com/paper/2410.13070/) (2024)
- [Forking Paths in Neural Text Generation](https://mlsanity.com/paper/2412.07961/) (2024)
- [Personalized Text Generation with Contrastive Activation Steering](https://mlsanity.com/paper/2503.05213/) (2025)
- [Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2502.12378/) (2025)
- [HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases](https://mlsanity.com/paper/2412.16311/) (2024)
- [Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models](https://mlsanity.com/paper/2410.01782/) (2024)
- [T-RAG: Lessons from the LLM Trenches](https://mlsanity.com/paper/2402.07483/) (2024)
- [Better Document-level Sentiment Analysis from RST Discourse Parsing](https://mlsanity.com/paper/1509.01599/) (2015)
- [DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2504.18243/) (2025)
- [MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System](https://mlsanity.com/paper/2503.09600/) (2025)
- [Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization](https://mlsanity.com/paper/2305.16784/) (2023)
- [RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation](https://mlsanity.com/paper/2502.10996/) (2025)
- [eRST: A Signaled Graph Theory of Discourse Relations and Organization](https://mlsanity.com/paper/2403.13560/) (2024)

## Built on by (most cited first, 1 of 1)

- [DynaWeb: Model-Based Reinforcement Learning of Web Agents](https://mlsanity.com/paper/2601.22149/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as an important means of enhancing the performance of large language models (LLMs) in knowledge-intensive tasks. However, most existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents. To overcome these limitations, we propose Disco-RAG, a discourse-aware framework that explicitly injects discourse signals into the generation process. Our method constructs intra-chunk discourse trees to capture local hierarchies and builds inter-chunk rhetorical graphs to model cross-passage coherence. These structures are jointly integrated into a planning blueprint that conditions the generation. Experiments on question answering and long-document summarization benchmarks show the efficacy of our approach. Disco-RAG achieves state-of-the-art results on the benchmarks without fine-tuning. These findings underscore the important role of discourse structure in advancing RAG systems.