REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives
Abstract
Wikipedia is an invaluable resource for factual information about a wide range of entities. However, the quality of articles on less-known entities often lags behind that of the well-known ones. This study proposes a novel approach to enhancing Wikipedia's B and C category biography articles by leveraging personal narratives such as autobiographies and biographies. By utilizing a multi-staged retrieval-augmented generation technique -- REVerSum -- we aim to enrich the informational content of these lesser-known articles. Our study reveals that personal narratives can significantly improve the quality of Wikipedia articles, providing a rich source of reliable information that has been underutilized in previous studies. Based on crowd-based evaluation, REVerSum generated content outperforms the best performing baseline by 17% in terms of integrability to the original Wikipedia article and 28.5\% in terms of informativeness. Code and Data are available at: https://github.com/sayantan11995/wikipedia_enrichment
Keywords
Cite
@article{arxiv.2502.12137,
title = {REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives},
author = {Sayantan Adak and Pauras Mangesh Meher and Paramita Das and Animesh Mukherjee},
journal= {arXiv preprint arXiv:2502.12137},
year = {2025}
}
Comments
Accepted at COLING2025 Industry Track