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

TL;DR

This paper introduces REVerSum, a multi-staged retrieval-augmented generation method that uses personal narratives to significantly improve the quality and informativeness of lesser-known Wikipedia biographies.

Contribution

The study presents a novel multi-staged retrieval-augmented generation approach leveraging personal narratives to enhance Wikipedia biographies of less-known entities.

Findings

REVerSum outperforms baseline by 17% in integrability.

REVerSum improves informativeness by 28.5%.

Personal narratives significantly enhance Wikipedia article quality.

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