With the growing success of Large Language models (LLMs) in information-seeking scenarios, search engines are now adopting generative approaches to provide answers along with in-line citations as attribution. While existing work focuses mainly on attributed question answering, in this paper, we target information-seeking scenarios which are often more challenging due to the open-ended nature of the queries and the size of the label space in terms of the diversity of candidate-attributed answers per query. We propose a reproducible framework to evaluate and benchmark attributed information seeking, using any backbone LLM, and different architectural designs: (1) Generate (2) Retrieve then Generate, and (3) Generate then Retrieve. Experiments using HAGRID, an attributed information-seeking dataset, show the impact of different scenarios on both the correctness and attributability of answers.
@article{arxiv.2409.08014,
title = {An Evaluation Framework for Attributed Information Retrieval using Large Language Models},
author = {Hanane Djeddal and Pierre Erbacher and Raouf Toukal and Laure Soulier and Karen Pinel-Sauvagnat and Sophia Katrenko and Lynda Tamine},
journal= {arXiv preprint arXiv:2409.08014},
year = {2024}
}