REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives

Publications

REVERSUM: A Multi-staged Retrieval-Augmented Generation Method to Enhance Wikipedia Tail Biographies through Personal Narratives

Author : Dr Paramita Das

Year : 2025

Publisher : Association for Computational Linguistics (ACL)

Source Title : Proceedings - International Conference on Computational Linguistics, COLING

Document Type :

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.