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

ACL ARR 2025 February Submission4786 Authors

Abstract:

We propose a simple, unsupervised method that injects pragmatic principles in retrieval-augmented generation (RAG) frameworks such as Dense Passage Retrieval~\cite{karpukhin2020densepassageretrievalopendomain} 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.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: Information Retrieval and Text Mining, Language Modeling, Question Answering, Discourse and Pragmatics

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 4786