GINGER: Grounded Information Nugget-Based Generation of Responses

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Łajewska, Weronika, Balog, Krisztian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908280265113600
author Łajewska, Weronika
Balog, Krisztian
author_facet Łajewska, Weronika
Balog, Krisztian
contents Retrieval-augmented generation (RAG) faces challenges related to factual correctness, source attribution, and response completeness. To address them, we propose a modular pipeline for grounded response generation that operates on information nuggets-minimal, atomic units of relevant information extracted from retrieved documents. The multistage pipeline encompasses nugget detection, clustering, ranking, top cluster summarization, and fluency enhancement. It guarantees grounding in specific facts, facilitates source attribution, and ensures maximum information inclusion within length constraints. Extensive experiments on the TREC RAG'24 dataset evaluated with the AutoNuggetizer framework demonstrate that GINGER achieves state-of-the-art performance on this benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18174
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GINGER: Grounded Information Nugget-Based Generation of Responses
Łajewska, Weronika
Balog, Krisztian
Computation and Language
Information Retrieval
Retrieval-augmented generation (RAG) faces challenges related to factual correctness, source attribution, and response completeness. To address them, we propose a modular pipeline for grounded response generation that operates on information nuggets-minimal, atomic units of relevant information extracted from retrieved documents. The multistage pipeline encompasses nugget detection, clustering, ranking, top cluster summarization, and fluency enhancement. It guarantees grounding in specific facts, facilitates source attribution, and ensures maximum information inclusion within length constraints. Extensive experiments on the TREC RAG'24 dataset evaluated with the AutoNuggetizer framework demonstrate that GINGER achieves state-of-the-art performance on this benchmark.
title GINGER: Grounded Information Nugget-Based Generation of Responses
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2503.18174