Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914159443050496 |
|---|---|
| author | Zhu, Yihua Liu, Qianying Aizawa, Akiko Shimodaira, Hidetoshi |
| author_facet | Zhu, Yihua Liu, Qianying Aizawa, Akiko Shimodaira, Hidetoshi |
| contents | 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 While LLM-only approaches offer generalization, they suffer from outdated knowledge, hallucinations, and lack of transparency.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 demonstrate that PDRR consistently outperforms existing methods across various LLM backbones and achieves superior performance on both chain-structured and non-chain complex questions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14099 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering Zhu, Yihua Liu, Qianying Aizawa, Akiko Shimodaira, Hidetoshi Computation and Language Information Retrieval 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 While LLM-only approaches offer generalization, they suffer from outdated knowledge, hallucinations, and lack of transparency.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 demonstrate that PDRR consistently outperforms existing methods across various LLM backbones and achieves superior performance on both chain-structured and non-chain complex questions. |
| title | Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2505.14099 |