UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responses

TL;DR

This paper introduces a modular retrieval-augmented generation pipeline that enhances factual accuracy and source attribution by focusing on information nuggets, tested within the LiveRAG Challenge framework.

Contribution

It presents a novel multistage pipeline for RAG that emphasizes information nuggets and improves context curation, addressing key challenges in factual correctness and response completeness.

Findings

Query rewriting boosts recall.

Using more documents beyond a point reduces effectiveness.

Pipeline enhances grounding and source attribution.

Abstract

Retrieval-augmented generation (RAG) faces challenges related to factual correctness, source attribution, and response completeness. The LiveRAG Challenge hosted at SIGIR'25 aims to advance RAG research using a fixed corpus and a shared, open-source LLM. We propose a modular pipeline that operates on information nuggets-minimal, atomic units of relevant information extracted from retrieved documents. This multistage pipeline encompasses query rewriting, passage retrieval and reranking, nugget detection and clustering, cluster ranking and summarization, and response fluency enhancement. This design inherently promotes grounding in specific facts, facilitates source attribution, and ensures maximum information inclusion within length constraints. In this challenge, we extend our focus to also address the retrieval component of RAG, building upon our prior work on multi-faceted query rewriting. Furthermore, for augmented generation, we concentrate on improving context curation capabilities, maximizing the breadth of information covered in the response while ensuring pipeline efficiency. Our results show that combining original queries with a few sub-query rewrites boosts recall, while increasing the number of documents used for reranking and generation beyond a certain point reduces effectiveness, without improving response quality.