{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJNQJQD3EGOQ7NZ6IYSHTWZGJN","short_pith_number":"pith:PJNQJQD3","schema_version":"1.0","canonical_sha256":"7a5b04c07b219d0fb73e462479db264b6b363f8b5ed5cdfa784267f37c709f3e","source":{"kind":"arxiv","id":"2407.15186","version":5},"attestation_state":"computed","paper":{"title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Shi, Nan Zhang, Xiaotong Zhang, Zhengju Tang, Zhi Yang","submitted_at":"2024-07-21T14:48:23Z","abstract_excerpt":"With the development of the Large Language Models (LLMs), a large range of LLM-based Text-to-SQL(Text2SQL) methods have emerged. This survey provides a comprehensive review of LLM-based Text2SQL studies. We first enumerate classic benchmarks and evaluation metrics. For the two mainstream methods, prompt engineering and finetuning, we introduce a comprehensive taxonomy and offer practical insights into each subcategory. We present an overall analysis of the above methods and various models evaluated on well-known datasets and extract some characteristics. Finally, we discuss the challenges and "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.15186","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-21T14:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"31e1dbb53a9cfb95576a44b7411449e158b843079b4676b8c58e7b84cd5bf1e0","abstract_canon_sha256":"358ce854abbad2243b333b62e78a981fc11639f3af6243d693e81c2e11376026"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:48.672582Z","signature_b64":"DnTEh7S9ikQYh34kwnSPn/mpw2RMncz6y+XNWvgsNd30Pn4PRP2HGFfYyd2mwVYtlf7mxxuu/W7lAMxJ4R2sCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a5b04c07b219d0fb73e462479db264b6b363f8b5ed5cdfa784267f37c709f3e","last_reissued_at":"2026-07-05T11:14:48.672116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:48.672116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liang Shi, Nan Zhang, Xiaotong Zhang, Zhengju Tang, Zhi Yang","submitted_at":"2024-07-21T14:48:23Z","abstract_excerpt":"With the development of the Large Language Models (LLMs), a large range of LLM-based Text-to-SQL(Text2SQL) methods have emerged. This survey provides a comprehensive review of LLM-based Text2SQL studies. We first enumerate classic benchmarks and evaluation metrics. For the two mainstream methods, prompt engineering and finetuning, we introduce a comprehensive taxonomy and offer practical insights into each subcategory. We present an overall analysis of the above methods and various models evaluated on well-known datasets and extract some characteristics. Finally, we discuss the challenges and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15186","kind":"arxiv","version":5},"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/2407.15186/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.15186","created_at":"2026-07-05T11:14:48.672172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15186v5","created_at":"2026-07-05T11:14:48.672172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15186","created_at":"2026-07-05T11:14:48.672172+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJNQJQD3EGOQ","created_at":"2026-07-05T11:14:48.672172+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJNQJQD3EGOQ7NZ6","created_at":"2026-07-05T11:14:48.672172+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJNQJQD3","created_at":"2026-07-05T11:14:48.672172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17094","citing_title":"LogCopilot: Automating Log Aggregation Analysis through Large Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":192,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN","json":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN.json","graph_json":"https://pith.science/api/pith-number/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/graph.json","events_json":"https://pith.science/api/pith-number/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/events.json","paper":"https://pith.science/paper/PJNQJQD3"},"agent_actions":{"view_html":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN","download_json":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN.json","view_paper":"https://pith.science/paper/PJNQJQD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15186&json=true","fetch_graph":"https://pith.science/api/pith-number/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/graph.json","fetch_events":"https://pith.science/api/pith-number/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/action/storage_attestation","attest_author":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/action/author_attestation","sign_citation":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/action/citation_signature","submit_replication":"https://pith.science/pith/PJNQJQD3EGOQ7NZ6IYSHTWZGJN/action/replication_record"}},"created_at":"2026-07-05T11:14:48.672172+00:00","updated_at":"2026-07-05T11:14:48.672172+00:00"}