mlsanityData to 7 Oct 2026

Structural Scaffolds for Citation Intent Classification in Scientific Publications

arXiv 1904.01608 ↗First posted 2 Apr 2019cs.CLcited by 129

Not on the map. Why?

Abstract (arXiv)

Identifying the intent of a citation in scientific papers (e.g., background information, use of methods, comparing results) is critical for machine reading of individual publications and automated analysis of the scientific literature. We propose structural scaffolds, a multitask model to incorporate structural information of scientific papers into citations for effective classification of citation intents. Our model achieves a new state-of-the-art on an existing ACL anthology dataset (ACL-ARC) with a 13.3% absolute increase in F1 score, without relying on external linguistic resources or hand-engineered features as done in existing methods. In addition, we introduce a new dataset of citation intents (SciCite) which is more than five times larger and covers multiple scientific domains compared with existing datasets. Our code and data are available at: https://github.com/allenai/scicite.

Key facts. Cited by 129 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 23; 2023: 19; 2024: 24; 2025: 18; 2026: 28.

129 papers.

Sort:

By area:

  1. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  2. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  3. 2021BERT: A Review of Applications in Natural Language Processing and Understandingcited by 109
  4. 2023The Semantic Scholar Open Data Platformcited by 109
  5. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  6. 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
  7. 2021What to Pre-Train on? Efficient Intermediate Task Selectioncited by 62
  8. 2022Data Curation Alone Can Stabilize In-context Learningcited by 58
  9. 2024Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learningcited by 47
  10. 2022Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Reviewcited by 37
  11. 2024SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literaturecited by 37
  12. 2022BigBIO: A Framework for Data-Centric Biomedical Natural Language Processingcited by 36
38 more
  1. 2021Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learningcited by 35
  2. 2021MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label settingcited by 30
  3. 2025CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoningcited by 28
  4. 2021Control Prefixes for Parameter-Efficient Text Generationcited by 23
  5. 2022The Diminishing Returns of Masked Language Models to Sciencecited by 22
  6. 2022CiteBench: A benchmark for Scientific Citation Text Generationcited by 22
  7. 2023Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneckcited by 21
  8. 2022Just Rank: Rethinking Evaluation with Word and Sentence Similaritiescited by 20
  9. 2023SPEC5G: A Dataset for 5G Cellular Network Protocol Analysiscited by 20
  10. 2024From Insights to Actions: The Impact of Interpretability and Analysis Research on NLPcited by 20
  11. 2024Data Contamination Report from the 2024 CONDA Shared Taskcited by 19
  12. 2024PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Paperscited by 18
  13. 2021CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understandingcited by 17
  14. 2022CORWA: A Citation-Oriented Related Work Annotation Datasetcited by 17
  15. 2024Related Work and Citation Text Generation: A Surveycited by 17
  16. 2023The ACL OCL Corpus: Advancing Open Science in Computational Linguisticscited by 16
  17. 2022CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervisioncited by 15
  18. 2021Learning from Multiple Noisy Partial Labelerscited by 14
  19. 2026Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAGcited by 14
  20. 2022Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Expertscited by 12
  21. 2023CitePrompt: Using Prompts to Identify Citation Intent in Scientific Paperscited by 12
  22. 2021Cross-Domain Multi-Task Learning for Sequential Sentence Classification in Research Paperscited by 11
  23. 2022VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understandingcited by 11
  24. 2023Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?cited by 11
  25. 2024Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarizationcited by 11
  26. 2024Model Balancing Helps Low-data Training and Fine-tuningcited by 11
  27. 2021Structure Inducing Pre-Trainingcited by 10
  28. 2022Representation Projection Invariance Mitigates Representation Collapsecited by 10
  29. 2024Abstention vs. Hallucination: Benchmarking LLM Source Attribution for Scientific Citationscited by 10
  30. 2021Towards Generating Citation Sentences for Multiple References with Intent Controlcited by 9
  31. 2022Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?cited by 9
  32. 2022Automatic Related Work Generation: A Meta Studycited by 8
  33. 2024Systematic Task Exploration with LLMs: A Study in Citation Text Generationcited by 8
  34. 2023Advancements in Scientific Controllable Text Generation Methodscited by 7
  35. 2024MedINST: Meta Dataset of Biomedical Instructionscited by 7
  36. 2022Automatic Rule Induction for Interpretable Semi-Supervised Learningcited by 6
  37. 2023PubGraph: A Large-Scale Scientific Knowledge Graphcited by 6
  38. 2023When Large Language Models Meet Citation: A Surveycited by 6

50 most cited of 129 All 129 (JSON)