EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hop-wise Planning with Iterative Explainable Self-Correction for Knowledge Base Question Answering

Dian Huang, Jianqi Gao, Xiangfeng Luo, Xinzhi Wang, Hao Wu, Hang Yu

ACM Transactions on Information Systems · 31.07.2026 · 44 (6) · 1-30

DOI: 10.1145/3819823 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 23.07.2026. Verfasst von Dian Huang und 5 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China Innovative Research Group Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowledge Base Question Answering (KBQA) aims to answer natural language questions by reasoning over large-scale structured Knowledge Bases (KBs). Among existing approaches, semantic parsing-based methods have emerged as a mainstream solution, where Large Language Models (LLMs) are employed to translate questions into structured graph queries such as Logical Forms (LFs). However, this paradigm faces two critical challenges: (1) The complex semantic mapping and graph retrieval operations render direct one-shot LF generation difficult; (2) LLMs suffer from inherent hallucination issues, generating semantically plausible-seeming but factually incorrect or invalid LFs, which are non-executable. To address these challenges, this article proposes HP-Corr , a novel framework that integrates H op-wise P lanning with iterative explainable self- Corr ection for faithful knowledge reasoning. Specifically, the system utilizes a fine-tuned open source LLM for query planning and explainable self-correction. The query planner generates reasoning paths hop-by-hop, while an explainable self-correction provides hop-wise feedback, enabling interpretable path editing based on existing reasoning paths and retrieved KB knowledge. By introducing the dual-module cooperative architecture, our system performs iterative plan-then-correct to refine query paths progressively, ensuring answer reliability and LFs executability. Experimental results demonstrate significant improvements, with our approach achieving higher accuracy while substantially reducing the search space, particularly in complex multi-hop KBQA scenarios.

Förderung

  • National Natural Science Foundation of China Innovative Research Group Project

Zitieren

APA

Huang, D., Gao, J., Luo, X., Wang, X., Wu, H., & Yu, H. (2026). Hop-wise Planning with Iterative Explainable Self-Correction for Knowledge Base Question Answering. ACM Transactions on Information Systems, 44(6), 1-30. https://doi.org/10.1145/3819823

Vancouver

Huang D, Gao J, Luo X, Wang X, Wu H, Yu H. Hop-wise Planning with Iterative Explainable Self-Correction for Knowledge Base Question Answering. ACM Transactions on Information Systems. 2026;44(6):1-30. doi:10.1145/3819823

BibTeX
@article{Huang2026,
  author = {Huang, Dian and Gao, Jianqi and Luo, Xiangfeng and Wang, Xinzhi and Wu, Hao and Yu, Hang},
  title = {Hop-wise Planning with Iterative Explainable Self-Correction for Knowledge Base Question Answering},
  journal = {ACM Transactions on Information Systems},
  year = {2026},
  volume = {44},
  number = {6},
  pages = {1--30},
  doi = {10.1145/3819823}
}
Kostenlos starten →