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

2025-02-17

AI Summary

To address the scarcity of reliable sources and sparse biographical content for low-traffic (B/C-class) Wikipedia biographies, this paper proposes REVerSum—the first systematic multi-stage retrieval-augmented generation (RAG) framework leveraging autobiographical and biographical narratives to enrich tail-end articles. Methodologically, it integrates semantic paragraph retrieval, controllable abstractive summarization, and Wikipedia-specific formatting alignment to enable fine-grained evidence localization and structured information injection. Its key contribution lies in formally establishing personal narratives as a credible supplementary source for Wikipedia and jointly optimizing retrieval precision and generation controllability. Experiments demonstrate that REVerSum outperforms the strongest baseline by 17% in information integrability and 28.5% in information richness. The code and dataset are publicly released.

Technology Category

• Natural Language Processing: Summarization
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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

Problem

• Enhance Wikipedia B, C category biographies
• Use personal narratives for content enrichment
• Improve article quality with REVerSum method

Innovation

• Multi-staged retrieval-augmented generation
• Leverages personal narratives
• Enhances Wikipedia biography articles