# CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers

arXiv: https://arxiv.org/abs/2304.12730 · HTML: https://mlsanity.com/paper/2304.12730/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 25 Apr 2023.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [WARP: Word-level Adversarial ReProgramming](https://mlsanity.com/paper/2101.00121/) (2021)
- [Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification](https://mlsanity.com/paper/2108.02035/) (2021)
- [OpenPrompt: An Open-source Framework for Prompt-learning](https://mlsanity.com/paper/2111.01998/) (2021)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [ImpactCite: An XLNet-based method for Citation Impact Analysis](https://mlsanity.com/paper/2005.06611/) (2020)

## Built on by (most cited first, 12 of 12)

- [Science Is Falling Behind the Frontier: Foundation Model Adoption Across Half a Million Papers](https://mlsanity.com/paper/2511.21739/) (2025)
- [Sci-Reasoning: A Dataset Decoding AI Innovation Patterns](https://mlsanity.com/paper/2601.04577/) (2026)
- [Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification](https://mlsanity.com/paper/2410.13332/) (2024)
- [CiteFusion: An Ensemble Framework for Citation Intent Classification Harnessing Dual-Model Binary Couples and SHAP Analyses](https://mlsanity.com/paper/2407.13329/) (2024)
- [Can LLMs Predict Citation Intent? An Experimental Analysis of In-context Learning and Fine-tuning on Open LLMs](https://mlsanity.com/paper/2502.14561/) (2025)
- [Enhancing AI Research Paper Analysis: Methodology Component Extraction using Factored Transformer-based Sequence Modeling Approach](https://mlsanity.com/paper/2311.03401/) (2023)
- [Leveraging GANs for citation intent classification and its impact on citation network analysis](https://mlsanity.com/paper/2505.21162/) (2025)
- [A Large-Scale Dataset and Citation Intent Classification in Turkish with LLMs](https://mlsanity.com/paper/2509.21907/) (2025)
- [Semantically Orthogonal Framework for Citation Classification: Disentangling Intent and Content](https://mlsanity.com/paper/2601.05103/) (2026)
- [Crystal: Characterizing Relative Impact of Scholarly Publications](https://mlsanity.com/paper/2603.26791/) (2026)
- [Reading Between the Citations: A Typed Claim Network for Scientific Literature](https://mlsanity.com/paper/2605.30966/) (2026)
- [Large Language Models for Citation Function Classification](https://mlsanity.com/paper/2607.17738/) (2026)

## Abstract (arXiv)

Citations in scientific papers not only help us trace the intellectual lineage but also are a useful indicator of the scientific significance of the work. Citation intents prove beneficial as they specify the role of the citation in a given context. In this paper, we present CitePrompt, a framework which uses the hitherto unexplored approach of prompt-based learning for citation intent classification. We argue that with the proper choice of the pretrained language model, the prompt template, and the prompt verbalizer, we can not only get results that are better than or comparable to those obtained with the state-of-the-art methods but also do it with much less exterior information about the scientific document. We report state-of-the-art results on the ACL-ARC dataset, and also show significant improvement on the SciCite dataset over all baseline models except one. As suitably large labelled datasets for citation intent classification can be quite hard to find, in a first, we propose the conversion of this task to the few-shot and zero-shot settings. For the ACL-ARC dataset, we report a 53.86% F1 score for the zero-shot setting, which improves to 63.61% and 66.99% for the 5-shot and 10-shot settings, respectively.