International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 2 (March-April 2025) Submit your research before last 3 days of April to publish your research paper in the issue of March-April.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 2
March-April 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

WebPedia 2.0: LLMs to Revolutionize Wikipedia Content Creation, Automating Knowledge Curation with Generative AI

Author(s) Prof. Dr. JAYANTHI KANNAN M.K, Mr. Anurodh Pancholi, Mr. Priyaanshu Singh
Country India
Abstract The WEBPEDIA (Synthesis of Topic-Oriented Role-based Multi-document Summarization) system is designed to produce structured summaries from multiple documents by organizing content according to topic and the roles of various stakeholders (e.g., government, media, public) involved in an event. The implementation begins with a Document Collection module that gathers relevant texts from different sources discussing the same event, ensuring a diverse, multi-perspective input. Next, the Topic Segmentation module uses techniques like TextRank and semantic clustering to break the content into coherent topic segments. The Role Identification module employs Named Entity Recognition (NER), dependency parsing, and rule-based methods to map entities to corresponding roles, such as identifying a political figure as part of the government perspective. Once roles are identified, the Role-based Content Selection module uses TF-IDF scores, semantic similarity, and topic-role alignment techniques to filter and select content that is most relevant to each identified role, removing redundant or off-topic text. For summary generation, WEBPEDIA combines template-based methods with neural text generation models such as BART or T5, which helps maintain fluency and coherence in the output while adhering to factual and logical flow. The final summary combines each role’s perspective into a comprehensive multi-document, multi-role narrative. For evaluation, the authors used datasets derived from real-world news coverage of complex events such as elections, pandemics, and protests. WEBPEDIA's performance was assessed using ROUGE metrics (ROUGE-1, ROUGE-2, ROUGE-L), as well as qualitative metrics like coverage and diversity to evaluate how well the summaries reflected all relevant roles and topics. Human evaluations further measured the fluency, coherence, and role accuracy of the summaries. The results showed that WEBPEDIA significantly outperforms traditional summarization baselines by generating summaries that are not only informative and factually consistent but also nuanced with multiple stakeholder perspectives, showcasing its effectiveness in complex information environment.
Keywords WebPedia 2.0, LLMs to Revolutionize Wikipedia, Content Creation Wikipedia, Automating Knowledge Curation, Generative AI, WEBpedia, Redefining Wikipedia, Crafting Wikipedia Articles with AI, Large Language Models.
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 7, Issue 2, March-April 2025
Published On 2025-04-22
DOI https://doi.org/10.36948/ijfmr.2025.v07i02.42262
Short DOI https://doi.org/g9gdrd
View / Download PDF File

Share this



E-ISSN 2582-2160
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 2Cover Page Vol 7 Isu 1Cover Page Vol 6 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijfmr.com