SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section
Not on the map. Why?
Abstract (arXiv)
Document summarization is a task to shorten texts into concise and informative summaries. This paper introduces a novel dataset designed for summarizing multiple scientific articles into a section of a survey. Our contributions are: (1) SurveySum, a new dataset addressing the gap in domain-specific summarization tools; (2) two specific pipelines to summarize scientific articles into a section of a survey; and (3) the evaluation of these pipelines using multiple metrics to compare their performance. Our results highlight the importance of high-quality retrieval stages and the impact of different configurations on the quality of generated summaries.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 14 of its 20 references that are in the map. First posted on arXiv 29 Aug 2024.
Builds on
14 of 20 references.
References · 14
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2017Billion-scale similarity search with GPUscited by 2,477
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
- 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
- 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 426
- 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
- 2019Document Expansion by Query Predictioncited by 225
- 2020Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articlescited by 96
- 2022An Empirical Survey on Long Document Summarization: Datasets, Models and Metricscited by 74
- 2019ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networkscited by 73
- 2020A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portalcited by 72
- 2023Generating a Structured Summary of Numerous Academic Papers: Dataset and Methodcited by 16
Built on by
Citing papers per year: 2025: 2.
2 papers.