Abstract
Answering Questions over Knowledge Graphs (KGQA) is key to well-functioning autonomous language agents in various real-life applications. To improve the neural-symbolic reasoning capabilities of language agents powered by Large Language Models (LLMs) in KGQA, we propose the Decomposition-Alignment-Reasoning Agent (DARA) framework. DARA effectively parses questions into formal queries through a dual mechanism: high-level iterative task decomposition and low-level task grounding. Importantly, DARA can be efficiently trained with a small number of high-quality reasoning trajectories. Our experimental results demonstrate that DARA fine-tuned on LLMs (e.g. Llama-2-7B, Mistral) outperforms both in-context learning-based agents with GPT-4 and alternative fine-tuned agents, across different benchmarks, making such models more accessible for real-life applications. We also show that DARA attains performance comparable to state-of-the-art enumerating-and-ranking-based methods for KGQA.- Anthology ID:
- 2024.findings-acl.203
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3406–3432
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.203
- DOI:
- 10.18653/v1/2024.findings-acl.203
- Cite (ACL):
- Haishuo Fang, Xiaodan Zhu, and Iryna Gurevych. 2024. DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3406–3432, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs (Fang et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-acl.203.pdf