EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection

Bingbing Wang, Jingjie Lin, Zhixin Bai, Xintong Song, Qianlong Wang, Min Yang, Xi Zeng, Jing Li, Ruifeng Xu

Transactions of the Association for Computational Linguistics · 05.03.2026 · 14 · 217-232

DOI: 10.1162/tacl.a.612 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 05.03.2026. Verfasst von Bingbing Wang und 8 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stance detection on social media plays a vital role in understanding public opinion on contentious topics. While prior work leverages external knowledge sources like Wikipedia to enrich limited target information, it primarily introduces conceptual content, neglecting the interpretability potential of knowledge and often leading to the incorporation of irrelevant or redundant information that hinders stance prediction performance. To address this, we introduce PiKGL, a Pruned interpretable Knowledge Graph Learning framework for explainable stance detection. Specifically, we first extract event triplets and topics to obtain real-world knowledge, which is then used to construct an interpretable knowledge graph. To ensure precision and minimize noise, we introduce a retrieval-guided pruning strategy that incorporates commonsense knowledge, filtering redundant information of the interpretable knowledge graph. Finally, the pruned knowledge graph is injected into a large language model to jointly model textual, target, and commonsense for improved stance comprehension. Experimental results conducted on three public datasets demonstrate our PiKGL achieves state-of-the-art performance on stance detection.

Zitieren

APA

Wang, B., Lin, J., Bai, Z., Song, X., Wang, Q., Yang, M., Zeng, X., Li, J., & Xu, R. (2026). PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection. Transactions of the Association for Computational Linguistics, 14, 217-232. https://doi.org/10.1162/tacl.a.612

Vancouver

Wang B, Lin J, Bai Z, Song X, Wang Q, Yang M, et al. PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection. Transactions of the Association for Computational Linguistics. 2026;14:217-232. doi:10.1162/tacl.a.612

BibTeX
@article{Wang2026,
  author = {Wang, Bingbing and Lin, Jingjie and Bai, Zhixin and Song, Xintong and Wang, Qianlong and Yang, Min and Zeng, Xi and Li, Jing and Xu, Ruifeng},
  title = {PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2026},
  volume = {14},
  pages = {217--232},
  doi = {10.1162/tacl.a.612}
}
Kostenlos starten →