BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916305162993664 |
|---|---|
| author | Chu, Zheng Chen, Jingchang Chen, Qianglong Wang, Haotian Zhu, Kun Du, Xiyuan Yu, Weijiang Liu, Ming Qin, Bing |
| author_facet | Chu, Zheng Chen, Jingchang Chen, Qianglong Wang, Haotian Zhu, Kun Du, Xiyuan Yu, Weijiang Liu, Ming Qin, Bing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19820 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering Chu, Zheng Chen, Jingchang Chen, Qianglong Wang, Haotian Zhu, Kun Du, Xiyuan Yu, Weijiang Liu, Ming Qin, Bing Computation and Language Artificial Intelligence 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. |
| title | BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.19820 |