arXiv:2402.14851
$R^3$: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks
원문 초록
Large Language Models (LLMs) have demonstrated strong performance on various tasks. To unleash their power on the Text-to-SQL task, we propose $R^3$ (Review-Rebuttal-Revision), a consensus-based multi-agent system for Text-to-SQL tasks. $R^3$ outperforms the existing single LLM Text-to-SQL systems as well as the multi-agent Text-to-SQL systems by $1.3\%$ to $8.1\%$ on Spider and Bird. Surprisingly, we find that for Llama-3-8B, $R^3$ outperforms chain-of-thought prompting by over 20\%, even outperforming GPT-3.5 on the development set of Spider.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SQL-o1: Automatic Text-to-SQL Program Synthesis via Self-Reward Heuristic Search
XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL
Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task
Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA
SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation
Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.