Lune

ACL Findings2024

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm

Yuanzhen Xie, Xinzhou Jin, Tao Xie, Mingxiong Lin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li

摘要

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 textto-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 brandnew 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: https://github.com/ FlyingFeather/DEA-SQL.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

已有 14 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。

可以从这些问题问起

Lune 可以查阅

全文 · 引用它的顶会 Paper · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration 引用了 DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
  • SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration 引用了 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
  • SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration 引用了 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction 引用了 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Reliable Text-to-SQL with Adaptive Abstention 引用了 DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
  • Reliable Text-to-SQL with Adaptive Abstention 引用了 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
  • SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL 引用了 DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
  • SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL 引用了 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
  • OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision 引用了 DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
  • OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision 引用了 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
  • OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate Supervision 引用了 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 引用了 DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
  • Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation 引用了 Training language models to follow instructions with human feedback
  • CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation 引用了 DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
  • CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation 引用了 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
  • CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation 引用了 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models 引用了 Training language models to follow instructions with human feedback
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

引用它的顶会 Paper14

  1. SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent CollaborationJipeng Cen, Jiaxin Liu, Zhixu Li, Jingjing WangAAAI 2025 · 18 次引用
  2. SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQLGe Qu, Jinyang Li, Bowen Qin, Xiaolong Li 等ACL 2025 · 13 次引用
  3. CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL TranslationHongwei Yuan, Xiu Tang, Ke Chen, Lidan Shou 等AAAI 2025 · 12 次引用
  4. Reliable Text-to-SQL with Adaptive AbstentionKaiwen Chen, Yueting Chen, Nick Koudas, Xiaohui YuSIGMOD 2025 · 9 次引用
  5. OpenSQL: Data-Efficient Text-to-SQL for Open-Source LLMs via Synthesized Intermediate SupervisionRuilin Hu, Yuyu Luo, Guoliang Li, Shuangqiao Wu 等VLDB 2026 · 4 次引用

它引用的 Paper10

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida 等NeurIPS 2022 · 24,707 次引用
  2. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 22,562 次引用
  3. DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-CorrectionMohammadreza Pourreza, Davood RafieiNeurIPS 2023 · 909 次引用
  4. Text-to-SQL Empowered by Large Language Models: A Benchmark EvaluationDawei Gao, Haibin Wang, Yaliang Li, Xiuyu Sun 等VLDB 2024 · 609 次引用
  5. A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language ModelsHaoran Xu, Young Jin Kim, Amr Sharaf, Hany Hassan AwadallaICLR 2024 · 122 次引用

相关 Paper

  1. Enhancing Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design StrategiesLinyong Nan, Yilun Zhao, Weijin Zou, Narutatsu Ri 等EMNLP Findings 2023 · 49 次引用
  2. ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-ThoughtHanchong Zhang, Ruisheng Cao, Lu Chen, Hongshen Xu 等EMNLP Findings 2023 · 54 次引用
  3. ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLYaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang 等ACL 2026 · 8 次引用
  4. Exploring Chain of Thought Style Prompting for Text-to-SQLChang-Yu Tai, Ziru Chen, Tianshu Zhang, Xiang Deng 等EMNLP 2023 · 35 次引用
  5. DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link GraphJihyung Lee, Jin-Seop Lee, Jaehoon Lee, YunSeok Choi 等ACL 2025
黄昏的海面,两侧是细线勾勒的悬崖