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.
View on arXiv@article{łajewska2025_2503.18174,
title={ GINGER: Grounded Information Nugget-Based Generation of Responses },
author={ Weronika Łajewska and Krisztian Balog },
journal={arXiv preprint arXiv:2503.18174},
year={ 2025 }
}