Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (41) · 35222-35229
DOI: 10.1609/aaai.v40i41.40829 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yihua Zhu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Knowledge Base Question Answering (KBQA) aims to answer natural language questions using structured knowledge from KBs. While LLM-only approaches offer generalization, they suffer from outdated knowledge, hallucinations, and lack of transparency. Chain-based KG-RAG methods address these issues by incorporating external KBs, but are limited to simple chain-structured questions due to the absence of planning and logical structuring. Inspired by semantic parsing methods, we propose PDRR: a four-stage framework consisting of Predict, Decompose, Retrieve, and Reason. Our method first predicts the question type and decomposes the question into structured triples. Then retrieves relevant information from KBs and guides the LLM as an agent to reason over and complete the decomposed triples. Experimental results show that our proposed KBQA model, PDRR, consistently outperforms existing methods across different LLM backbones and achieves superior performance on various types of questions.
Zitieren
APA
Zhu, Y., Liu, Q., Aizawa, A., & Shimodaira, H. (2026). Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 35222-35229. https://doi.org/10.1609/aaai.v40i41.40829
Vancouver
Zhu Y, Liu Q, Aizawa A, Shimodaira H. Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(41):35222-35229. doi:10.1609/aaai.v40i41.40829
BibTeX
@article{Zhu2026,
author = {Zhu, Yihua and Liu, Qianying and Aizawa, Akiko and Shimodaira, Hidetoshi},
title = {Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {41},
pages = {35222--35229},
doi = {10.1609/aaai.v40i41.40829}
}
EUVIMED