Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm
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_ | 1866929407231262720 |
|---|---|
| author | Xie, Yuanzhen Jin, Xinzhou Xie, Tao Lin, MingXiong Chen, Liang Yu, Chenyun Cheng, Lei Zhuo, ChengXiang Hu, Bo Li, Zang |
| author_facet | Xie, Yuanzhen Jin, Xinzhou Xie, Tao Lin, MingXiong Chen, Liang Yu, Chenyun Cheng, Lei Zhuo, ChengXiang Hu, Bo Li, Zang |
| contents | In-context learning of large-language models (LLMs) has achieved remarkable success in the field of natural language processing, while extensive case studies reveal that the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL. To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition. Specifically, the information determination module for eliminating redundant information and the brand-new prompt structure based on problem classification greatly enhance the model's attention. Additionally, the inclusion of self-correction and active learning modules greatly expands the problem-solving scope of LLMs, hence improving the upper limit of LLM-based approaches. Extensive experiments conducted on three datasets demonstrate that our approach outperforms other methods by a significant margin. About 2-3 percentage point improvements compared to the existing baseline on the Spider Dev, Spider-Realistic, and Bird Dev datasets and new SOTA results on the Spider Test dataset are achieved. Our code is available on GitHub: \url{https://github.com/FlyingFeather/DEA-SQL}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10671 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm Xie, Yuanzhen Jin, Xinzhou Xie, Tao Lin, MingXiong Chen, Liang Yu, Chenyun Cheng, Lei Zhuo, ChengXiang Hu, Bo Li, Zang Computation and Language In-context learning of large-language models (LLMs) has achieved remarkable success in the field of natural language processing, while extensive case studies reveal that the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL. To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition. Specifically, the information determination module for eliminating redundant information and the brand-new prompt structure based on problem classification greatly enhance the model's attention. Additionally, the inclusion of self-correction and active learning modules greatly expands the problem-solving scope of LLMs, hence improving the upper limit of LLM-based approaches. Extensive experiments conducted on three datasets demonstrate that our approach outperforms other methods by a significant margin. About 2-3 percentage point improvements compared to the existing baseline on the Spider Dev, Spider-Realistic, and Bird Dev datasets and new SOTA results on the Spider Test dataset are achieved. Our code is available on GitHub: \url{https://github.com/FlyingFeather/DEA-SQL}. |
| title | Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.10671 |