{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/leveraging-prior-experience-an-expandable","title":"Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL","arxiv_id":"2411.13244","date":"2024-11-20","proceeding":null,"authors":["Zhibo Chu","Zichong Wang","Qitao Qin"],"abstract":"Large Language Models (LLMs) exhibit impressive problem-solving skills across many tasks, but they still underperform compared to humans in various downstream applications, such as text-to-SQL. On the BIRD benchmark leaderboard, human performance achieves an accuracy of 92.96\\%, whereas the top-performing method reaches only 72.39\\%. Notably, these state-of-the-art (SoTA) methods predominantly rely on in-context learning to simulate human-like reasoning. However, they overlook a critical human skill: continual learning. Inspired by the educational practice of maintaining mistake notebooks during our formative years, we propose LPE-SQL (Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL), a novel framework designed to augment LLMs by enabling continual learning without requiring parameter fine-tuning. LPE-SQL consists of four modules that \\textbf{i)} retrieve relevant entries, \\textbf{ii)} efficient sql generation, \\textbf{iii)} generate the final result through a cross-consistency mechanism and \\textbf{iv)} log successful and failed tasks along with their reasoning processes or reflection-generated tips. Importantly, the core module of LPE-SQL is the fourth one, while the other modules employ foundational methods, allowing LPE-SQL to be easily integrated with SoTA technologies to further enhance performance. Our experimental results demonstrate that this continual learning approach yields substantial performance gains, with the smaller Llama-3.1-70B model with surpassing the performance of the larger Llama-3.1-405B model using SoTA methods.","url_abs":"https://arxiv.org/abs/2411.13244v1","url_pdf":"https://arxiv.org/pdf/2411.13244v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"leveraging-prior-experience-an-expandable","repo_url":"https://github.com/czbnlp/LPE-SQL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"text-to-sql","task_name":"Text to SQL"},{"task_slug":"text-to-sql","task_name":"Text-To-SQL"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.13244","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}