mlsanityData to 7 Oct 2026

Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation

arXiv 2502.17839 ↗First posted 25 Feb 2025cs.CL cs.AI cs.LGcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

We propose a simple, unsupervised method that injects pragmatic principles in retrieval-augmented generation (RAG) frameworks such as Dense Passage Retrieval to enhance the utility of retrieved contexts. Our approach first identifies which sentences in a pool of documents retrieved by RAG are most relevant to the question at hand, cover all the topics addressed in the input question and no more, and then highlights these sentences within their context, before they are provided to the LLM, without truncating or altering the context in any other way. We show that this simple idea brings consistent improvements in experiments on three question answering tasks (ARC-Challenge, PubHealth and PopQA) using five different LLMs. It notably enhances relative accuracy by up to 19.7% on PubHealth and 10% on ARC-Challenge compared to a conventional RAG system.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 21 of its 55 references that are in the map. First posted on arXiv 25 Feb 2025.

Builds on

21 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 20

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  10. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  11. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  12. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 339
8 more
  1. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  2. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  3. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  4. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solverscited by 137
  5. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinementcited by 38
  6. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25
  7. 2020Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answeringcited by 24
  8. 2018Neural models of factualitycited by 20

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  2. 2024In Defense of RAG in the Era of Long-Context Language Models
  3. 2025On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems
  4. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
  5. 2024Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis
  6. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation
  7. 2024Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
  8. 2025RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning