• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Anderes
  4. Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization
 
  • Details
  • Full
Options
2025
Paper (Preprint, Research Paper, Review Paper, White Paper, etc.)
Title

Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization

Title Supplement
Published on arXiv
Abstract
The exponential growth of scientific publications has made it increasingly difficult for researchers to stay updated and synthesize knowledge effectively. This paper presents XSum, a modular pipeline for multi-document summarization (MDS) in the scientific domain using Retrieval-Augmented Generation (RAG). The pipeline includes two core components: a question-generation module and an editor module. The question-generation module dynamically generates questions adapted to the input papers, ensuring the retrieval of relevant and accurate information. The editor module synthesizes the retrieved content into coherent and well-structured summaries that adhere to academic standards for proper citation. Evaluated on the SurveySum dataset, XSum demonstrates strong performance, achieving considerable improvements in metrics such as CheckEval, G-Eval and Ref-F1 compared to existing approaches. This work provides a transparent, adaptable framework for scientific summarization with potential applications in a wide range of domains. Code available at https://github.com/webis-de/scolia25-xsum
Author(s)
Achkar, Pierre  orcid-logo
Fraunhofer-Institut für System- und Innovationsforschung ISI  
Gollub, Tim
Bauhaus-Universität Weimar
Potthast, Martin
Universität Kassel  
Conference
International Workshop on Scholarly Information Access 2025  
European Conference on Information Retrieval 2025  
Open Access
File(s)
Download (1.12 MB)
Rights
CC BY 4.0: Creative Commons Attribution
DOI
10.48550/arXiv.2505.16349
10.24406/publica-4721
Language
English
Fraunhofer-Institut für System- und Innovationsforschung ISI  
Keyword(s)
  • Multi-document Summarization (MDS)

  • Retrieval-Augmented Generation (RAG)

  • Scientific Literature Summarization

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024