🤖 AI Summary
This study addresses the conflation of citation intent and cited content type in existing citation classification methods, which hinders both fine-grained distinction and classification reliability. To resolve this, the authors propose SOFT, a novel framework grounded in semantic role theory that decouples citation intent and content type into an orthogonal two-dimensional classification scheme, establishing clear and reusable annotation guidelines. Through manual re-annotation of the ACL-ARC dataset and the creation of a cross-disciplinary ACT2 test set, the authors evaluate SOFT using both zero-shot and fine-tuned large language models. Results demonstrate that SOFT significantly outperforms existing frameworks such as ACL-ARC and SciCite in enhancing agreement between human annotators and models, improving classification performance, and enabling robust cross-domain generalization.
📝 Abstract
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.