@inproceedings{gao-etal-2025-tdcsa,
    title = "{TDCSA}: {LLM}-Guided Top-Down Approach for Robust Citation Sentiment Analysis",
    author = "Gao, Fan  and
      Peng, Jieyang  and
      Tao, Xiaoming  and
      Youzheng, Wang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.335/",
    pages = "6467--6484",
    ISBN = "979-8-89176-256-5",
    abstract = "Citation Sentiment Analysis (CSA) plays a crucial role in understanding academic influence and knowledge diffusion. While pre-trained language models (PLMs) and large language models (LLMs) showed remarkable success in general sentiment analysis, they encounter specialized challenges in CSA due to the less significant and implicit sentiment expressions in academic writing, as well as complex sentiment transitions. {\%} importance {\&} limitations In order to address the challenges, We propose TDCSA, a Top-Down framework that leverages LLMs' semantic understanding capabilities to enhance PLM-based CSA, which transforms the traditional bottom-up feature engineering paradigm into a top-down architecture. {\%} what we do Our framework consists of three key components: (1) a Dual LLM Feature Generation module for robust quadruple extraction, (2) a Multi-view Feature Representation mechanism for neutral citation processing, and (3) a Quad Feature Enhanced PLM. {\%} how we do Experiments demonstrate that TDCSA significantly outperforms existing methods, achieving state-of-the-art performance while maintaining robustness to quadruple quality variations."
}