Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature Summarization
This work addresses the problem of efficient knowledge synthesis for researchers, offering a transparent and adaptable framework, though it appears incremental as it builds on existing RAG and modular approaches.
The paper tackles the challenge of synthesizing knowledge from the growing volume of scientific publications by introducing XSum, a modular pipeline for multi-document summarization using Retrieval-Augmented Generation, which achieved considerable improvements in metrics like CheckEval, G-Eval, and Ref-F1 on the SurveySum dataset.
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