{"paper":{"title":"Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianbin Qin, Min Yang, Tianhao Qiu, Tianle Wang, Xiaojun Chen","submitted_at":"2024-05-04T15:40:17Z","abstract_excerpt":"Despite the success of large language models (LLMs) in Text-to-SQL tasks, open-source LLMs encounter challenges in contextual understanding and response coherence. To tackle these issues, we present \\ours, a systematic methodology tailored for Text-to-SQL with open-source LLMs. Our contributions include a comprehensive evaluation of open-source LLMs in Text-to-SQL tasks, the \\openprompt strategy for effective question representation, and novel strategies for supervised fine-tuning. We explore the benefits of Chain-of-Thought in step-by-step inference and propose the \\openexample method for enh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06674","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.06674/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}