Large Language Models for Citation Function Classification

• URL: http://arxiv.org/abs/2607.17738v1
• Date: Mon, 20 Jul 2026 09:29:53 GMT
• Title: Large Language Models for Citation Function Classification
• Abstract summary: Citation function classification plays a crucial role in understanding the relationships between scientific publications and advancing bibliometric analysis.<n>This study presents one of the first comprehensive evaluations of multiple state-of-the-art (SOTA) large language models (LLMs) for citation function classification.<n>Our fine-tuned Falcon 7B model achieves a 73.3% macro F1 score on ACL-ARC, representing a significant improvement over previous methods.
• Score: 5.884448754842615
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Citation function classification plays a crucial role in understanding the relationships between scientific publications and advancing bibliometric analysis. This study presents one of the first comprehensive evaluations of multiple state-of-the-art (SOTA) large language models (LLMs) for citation function classification, achieving new SOTA results on the ACL-ARC dataset. We systematically compare five models (Mistral 7B, Orca 2-7B, LLaMA 3.1-8B, Falcon 7B, and SciBERT) across zero-shot, few-shot, and fine-tuning approaches. Our fine-tuned Falcon 7B model achieves a 73.3% macro F1 score on ACL-ARC, representing a significant improvement over previous methods. Additionally, we introduce AC3, a novel dataset featuring a seven-category annotation scheme that distinguishes between neutral acknowledgments and explicit evaluative stances (more opinion-oriented citations - criticizing, complimenting, contradicting). The dataset is implemented across four context extraction variants to systematically evaluate the impact of contextual scope on classification performance. We also provide detailed analysis of model performance, experimental configurations, and limitations to guide future research in this domain. To our knowledge, this is one of the first studies dedicated to comprehensive model comparison for citation function classification, addressing a gap identified in recent surveys.

Related papers

• Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting [4.14197005718384]
  Aspect-Category Sentiment Analysis (ACSA) provides granular insights by identifying specific themes within reviews and their associated sentiment.<n>We argue that leveraging large language models (LLMs) in a zero-shot setting is a practical alternative where resources for data annotation are limited.<n>We propose a novel Chain-of-Thought (CoT) prompting technique that utilise an intermediate Unified Meaning Representation (UMR) to structure the reasoning process for the ACSA task.
  arXiv  Detail & Related papers  (2025-12-22T18:23:37Z)
• Benchmarking Vision-Language and Multimodal Large Language Models in Zero-shot and Few-shot Scenarios: A study on Christian Iconography [0.764671395172401]
  This study evaluates the capabilities of Multimodal Large Language Models (LLMs) and Vision Language Models (VLMs) in single-label classification of Christian Iconography.
  arXiv  Detail & Related papers  (2025-09-23T09:23:31Z)
• Unraveling the Capabilities of Language Models in News Summarization [0.0]
  This work provides a comprehensive benchmarking of 20 recent language models, focusing on smaller ones for the news summarization task.<n>We focus in this study on zero-shot and few-shot learning settings and we apply a robust evaluation methodology.<n>We highlight the exceptional performance of GPT-3.5-Turbo and GPT-4, which generally dominate due to their advanced capabilities.
  arXiv  Detail & Related papers  (2025-01-30T04:20:16Z)
• Language Model Preference Evaluation with Multiple Weak Evaluators [89.90733463933431]
  We introduce PGED, a novel approach that leverages multiple model-based evaluators to construct preference graphs, and then ensembles and denoises these graphs for acyclic, non-contradictory evaluation results.<n>We demonstrate PGED's superiority in three applications: 1) model ranking for evaluation, 2) response selection for test-time scaling, and 3) data selection for model fine-tuning.
  arXiv  Detail & Related papers  (2024-10-14T01:57:25Z)
• Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions [62.12545440385489]
  Large language models (LLMs) have brought substantial advancements in text generation, but their potential for enhancing classification tasks remains underexplored. We propose a framework for thoroughly investigating fine-tuning LLMs for classification, including both generation- and encoding-based approaches. We instantiate this framework in edit intent classification (EIC), a challenging and underexplored classification task.
  arXiv  Detail & Related papers  (2024-10-02T20:48:28Z)
• On the Evaluation Consistency of Attribution-based Explanations [42.1421504321572]
  We introduce Meta-Rank, an open platform for benchmarking attribution methods in the image domain. Our benchmark reveals three insights in attribution evaluation endeavors: 1) evaluating attribution methods under disparate settings can yield divergent performance rankings; 2) although inconsistent across numerous cases, the performance rankings exhibit remarkable consistency across distinct checkpoints along the same training trajectory; and 3) prior attempts at consistent evaluation fare no better than baselines when extended to more heterogeneous models and datasets.
  arXiv  Detail & Related papers  (2024-07-28T11:49:06Z)
• CiteFusion: An Ensemble Framework for Citation Intent Classification Harnessing Dual-Model Binary Couples and SHAP Analyses [1.6695303704829412]
  CiteFusion addresses the multi-class Citation Intent Classification task on two benchmark datasets: SciCite and ACL-ARC.<n>Experiments show that CiteFusion achieves state-of-the-art performance, with Macro-F1 scores of 89.60% on SciCite, and 76.24% on ACL-ARC.<n>We release a web-based application that classifies citation intents leveraging the CiteFusion models developed on SciCite.
  arXiv  Detail & Related papers  (2024-07-18T09:29:33Z)
• Anchor Points: Benchmarking Models with Much Fewer Examples [88.02417913161356]
  In six popular language classification benchmarks, model confidence in the correct class on many pairs of points is strongly correlated across models. We propose Anchor Point Selection, a technique to select small subsets of datasets that capture model behavior across the entire dataset. Just several anchor points can be used to estimate model per-class predictions on all other points in a dataset with low mean absolute error.
  arXiv  Detail & Related papers  (2023-09-14T17:45:51Z)
• News Summarization and Evaluation in the Era of GPT-3 [73.48220043216087]
  We study how GPT-3 compares against fine-tuned models trained on large summarization datasets. We show that not only do humans overwhelmingly prefer GPT-3 summaries, prompted using only a task description, but these also do not suffer from common dataset-specific issues such as poor factuality.
  arXiv  Detail & Related papers  (2022-09-26T01:04:52Z)
• CoPHE: A Count-Preserving Hierarchical Evaluation Metric in Large-Scale Multi-Label Text Classification [70.554573538777]
  We argue for hierarchical evaluation of the predictions of neural LMTC models. We describe a structural issue in the representation of the structured label space in prior art. We propose a set of metrics for hierarchical evaluation using the depth-based representation.
  arXiv  Detail & Related papers  (2021-09-10T13:09:12Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.