# What's New? Summarizing Contributions in Scientific Literature

arXiv: https://arxiv.org/abs/2011.03161 · HTML: https://mlsanity.com/paper/2011.03161/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [LimGen: Probing the LLMs for Generating Suggestive Limitations of Research Papers](https://mlsanity.com/paper/2403.15529/) (2024)
- [SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation](https://mlsanity.com/paper/2403.17768/) (2024)
- [Acceleron: A Tool to Accelerate Research Ideation](https://mlsanity.com/paper/2403.04382/) (2024)
- [Hierarchical Tree-structured Knowledge Graph For Academic Insight Survey](https://mlsanity.com/paper/2402.04854/) (2024)
- [The State and Fate of Summarization Datasets: A Survey](https://mlsanity.com/paper/2411.04585/) (2024)
- [Background Summarization of Event Timelines](https://mlsanity.com/paper/2310.16197/) (2023)
- [Fish-bone diagram of research issue: Gain a bird's-eye view on a specific research topic](https://mlsanity.com/paper/2407.01553/) (2024)
- [VerbCL: A Dataset of Verbatim Quotes for Highlight Extraction in Case Law](https://mlsanity.com/paper/2108.10120/) (2021)

## Abstract (arXiv)

With thousands of academic articles shared on a daily basis, it has become increasingly difficult to keep up with the latest scientific findings. To overcome this problem, we introduce a new task of disentangled paper summarization, which seeks to generate separate summaries for the paper contributions and the context of the work, making it easier to identify the key findings shared in articles. For this purpose, we extend the S2ORC corpus of academic articles, which spans a diverse set of domains ranging from economics to psychology, by adding disentangled "contribution" and "context" reference labels. Together with the dataset, we introduce and analyze three baseline approaches: 1) a unified model controlled by input code prefixes, 2) a model with separate generation heads specialized in generating the disentangled outputs, and 3) a training strategy that guides the model using additional supervision coming from inbound and outbound citations. We also propose a comprehensive automatic evaluation protocol which reports the relevance, novelty, and disentanglement of generated outputs. Through a human study involving expert annotators, we show that in 79%, of cases our new task is considered more helpful than traditional scientific paper summarization.