# Semantically Orthogonal Framework for Citation Classification: Disentangling Intent and Content

arXiv: https://arxiv.org/abs/2601.05103 · HTML: https://mlsanity.com/paper/2601.05103/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 63 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models](https://mlsanity.com/paper/2005.02507/) (2020)
- [Benchmarking Object Detectors with COCO: A New Path Forward](https://mlsanity.com/paper/2403.18819/) (2024)
- [CrossRE: A Cross-Domain Dataset for Relation Extraction](https://mlsanity.com/paper/2210.09345/) (2022)
- [A Survey on Evaluation of Out-of-Distribution Generalization](https://mlsanity.com/paper/2403.01874/) (2024)
- [CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems](https://mlsanity.com/paper/2010.05139/) (2020)
- [CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers](https://mlsanity.com/paper/2304.12730/) (2023)
- [ObjectLab: Automated Diagnosis of Mislabeled Images in Object Detection Data](https://mlsanity.com/paper/2309.00832/) (2023)
- [CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Dataset](https://mlsanity.com/paper/2310.16225/) (2023)
- [Benchmarking a Benchmark: How Reliable is MS-COCO?](https://mlsanity.com/paper/2311.02709/) (2023)
- [Academic information retrieval using citation clusters: In-depth evaluation based on systematic reviews](https://mlsanity.com/paper/2207.03299/) (2022)
- [Beyond Dataset Creation: Critical View of Annotation Variation and Bias Probing of a Dataset for Online Radical Content Detection](https://mlsanity.com/paper/2412.11745/) (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)
- [Joint Dropout: Improving Generalizability in Low-Resource Neural Machine Translation through Phrase Pair Variables](https://mlsanity.com/paper/2307.12835/) (2023)

## Abstract (arXiv)

Understanding the role of citations is essential for research assessment and citation-aware digital libraries. However, existing citation classification frameworks often conflate citation intent (why a work is cited) with cited content type (what part is cited), limiting their effectiveness in auto classification due to a dilemma between fine-grained type distinctions and practical classification reliability. We introduce SOFT, a Semantically Orthogonal Framework with Two dimensions that explicitly separates citation intent from cited content type, drawing inspiration from semantic role theory. We systematically re-annotate the ACL-ARC dataset using SOFT and release a cross-disciplinary test set sampled from ACT2. Evaluation with both zero-shot and fine-tuned Large Language Models demonstrates that SOFT enables higher agreement between human annotators and LLMs, and supports stronger classification performance and robust cross-domain generalization compared to ACL-ARC and SciCite annotation frameworks. These results confirm SOFT's value as a clear, reusable annotation standard, improving clarity, consistency, and generalizability for digital libraries and scholarly communication infrastructures. All code and data are publicly available on GitHub https://github.com/zhiyintan/SOFT.