mlsanityData to 7 Oct 2026

Explaining Relationships Among Research Papers

arXiv 2402.13426 ↗First posted 20 Feb 2024cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Due to the rapid pace of research publications, keeping up to date with all the latest related papers is very time-consuming, even with daily feed tools. There is a need for automatically generated, short, customized literature reviews of sets of papers to help researchers decide what to read. While several works in the last decade have addressed the task of explaining a single research paper, usually in the context of another paper citing it, the relationship among multiple papers has been ignored; prior works have focused on generating a single citation sentence in isolation, without addressing the expository and transition sentences needed to connect multiple papers in a coherent story. In this work, we explore a feature-based, LLM-prompting approach to generate richer citation texts, as well as generating multiple citations at once to capture the complex relationships among research papers. We perform an expert evaluation to investigate the impact of our proposed features on the quality of the generated paragraphs and find a strong correlation between human preference and integrative writing style, suggesting that humans prefer high-level, abstract citations, with transition sentences between them to provide an overall story.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 67 references that are in the map. First posted on arXiv 20 Feb 2024.

Builds on

32 of 67 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  6. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  7. 2018Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategiescited by 292
  8. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  9. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 233
  10. 2020Provable Meta-Learning of Linear Representationscited by 161
  11. 2019Structural Scaffolds for Citation Intent Classification in Scientific Publicationscited by 129
  12. 2019ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networkscited by 73
20 more
  1. 2021Understanding Hard Negatives in Noise Contrastive Estimationcited by 39
  2. 2020Explaining Relationships Between Scientific Documentscited by 35
  3. 2022Investigating self-supervised learning for speech enhancement and separationcited by 35
  4. 2021Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documentscited by 33
  5. 2021MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label settingcited by 30
  6. 2023Explanation-based Finetuning Makes Models More Robust to Spurious Cuescited by 24
  7. 2022Target-aware Abstractive Related Work Generation with Contrastive Learningcited by 20
  8. 2022CORWA: A Citation-Oriented Related Work Annotation Datasetcited by 17
  9. 2022Computing Medial Axis Transform with Feature Preservation via Restricted Power Diagramcited by 15
  10. 2022CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrievalcited by 14
  11. 2021Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generationcited by 13
  12. 2022Learning ASR pathways: A sparse multilingual ASR modelcited by 12
  13. 2022Reinforcement Learning with Automated Auxiliary Loss Searchcited by 12
  14. 2023Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interactioncited by 10
  15. 2019Neural Related Work Summarization with a Joint Context-driven Attention Mechanismcited by 9
  16. 2019The CL-SciSumm Shared Task 2018: Results and Key Insightscited by 9
  17. 2022Few-Shot Document-Level Event Argument Extractioncited by 9
  18. 2022Parameter-Efficient Tuning with Special Token Adaptationcited by 7
  19. 2018Siamese Networks for Semantic Pattern Similaritycited by 6
  20. 2022End-to-End Neural Discourse Deixis Resolution in Dialoguecited by 1

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  2. 2025Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Modelscited by 7
  3. 2025Modelling and Classifying the Components of a Literature Reviewcited by 2