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

Haris Riaz, Ellen Riloff, Mihai Surdeanu
2/25/2025
cs.CLcs.AIcs.LG

No official code found. Best implementation: hriaz17/SayLessRAG (1 star, MIT, last commit 2025-03-02).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

hriaz17/SayLessRAGCommunity67%
MIT

Code for the paper: "Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation"

10Jan 11, 20251 years agoMIT
dense-retrievalgricean-pragmaticsinformation-extractioninformation-retrievalllm-reasoning+2 more

Similar Papers

Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA

83% match2024

Enhancing Retrieval-Augmented Generation: A Study of Best Practices

83% match1 repo1072025

SAGE: A Framework of Precise Retrieval for RAG

83% match2025

Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation

83% match1 repo102024

Provence: efficient and robust context pruning for retrieval-augmented generation

82% match2025

On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems

82% match1 repo72025

Cite this paper

@article{riaz2025less,
  title  = {Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation},
  author = {Haris Riaz and Ellen Riloff and Mihai Surdeanu},
  year   = {2025},
  eprint = {2502.17839},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.17839v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.17839.svg)](https://codeofpaper.com/paper/2502.17839)

Discussion