BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering

Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, Bing Qin


Abstract
Large language models (LLMs) have demonstrated strong reasoning capabilities.Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks.Retrieval-augmented reasoning represents a promising approach.However, significant challenges still persist, including inaccurate and insufficient retrieval for complex questions, as well as difficulty in integrating multi-source knowledge.To address this, we propose Beam Aggregation Reasoning (BeamAggR), a reasoning framework for knowledge-intensive multi-hop QA.BeamAggR explores and prioritizes promising answers at each hop of question.Concretely, we parse the complex questions into trees, which include atom and composite questions, followed by bottom-up reasoning.For atomic questions, the LLM conducts reasoning on multi-source knowledge to get answer candidates.For composite questions, the LLM combines beam candidates, explores multiple reasoning paths through probabilistic aggregation, and prioritizes the most promising trajectory.Extensive experiments on four open-domain multi-hop reasoning datasets show that our method significantly outperforms SOTA methods by 8.5%.Furthermore, our analysis reveals that BeamAggR elicits better knowledge collaboration and answer aggregation.
Anthology ID:
2024.acl-long.67
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1229–1248
Language:
URL:
https://aclanthology.org/2024.acl-long.67
DOI:
10.18653/v1/2024.acl-long.67
Bibkey:
Cite (ACL):
Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, and Bing Qin. 2024. BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1229–1248, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering (Chu et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.67.pdf