{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IDAK5TLMDQQV2JFS53N4W6NSJK","short_pith_number":"pith:IDAK5TLM","schema_version":"1.0","canonical_sha256":"40c0aecd6c1c215d24b2eedbcb79b24ab0baf0d72eefda59645410198987452d","source":{"kind":"arxiv","id":"2405.15307","version":1},"attestation_state":"computed","paper":{"title":"Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Li, Bowen Qin, Chenhao Ma, Ge Qu, Jinyang Li, Nan Huo, Reynold Cheng","submitted_at":"2024-05-24T07:51:08Z","abstract_excerpt":"Large Language Models (LLMs) driven by In-Context Learning (ICL) have significantly improved the performance of text-to-SQL. Previous methods generally employ a two-stage reasoning framework, namely 1) schema linking and 2) logical synthesis, making the framework not only effective but also interpretable. Despite these advancements, the inherent bad nature of the generalization of LLMs often results in hallucinations, which limits the full potential of LLMs. In this work, we first identify and categorize the common types of hallucinations at each stage in text-to-SQL. We then introduce a novel"},"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":"2405.15307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T07:51:08Z","cross_cats_sorted":[],"title_canon_sha256":"0ebe45e71d1b06944fb7976238ece2dd039af4fc2df43f0a71105a494fb6052d","abstract_canon_sha256":"16781bf496144149f2bb60feada00e341ce8f1a66d26bbcce1d70d5738635cbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:47.554592Z","signature_b64":"KyEJcdEhW75UBCc0EttqxNCLMLgTaDhuontRvLktlkRYRUSSd60mQiw9MgR7fClDflWrZFjdB8/mpH0A7WDUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40c0aecd6c1c215d24b2eedbcb79b24ab0baf0d72eefda59645410198987452d","last_reissued_at":"2026-07-05T08:22:47.554131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:47.554131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Li, Bowen Qin, Chenhao Ma, Ge Qu, Jinyang Li, Nan Huo, Reynold Cheng","submitted_at":"2024-05-24T07:51:08Z","abstract_excerpt":"Large Language Models (LLMs) driven by In-Context Learning (ICL) have significantly improved the performance of text-to-SQL. Previous methods generally employ a two-stage reasoning framework, namely 1) schema linking and 2) logical synthesis, making the framework not only effective but also interpretable. Despite these advancements, the inherent bad nature of the generalization of LLMs often results in hallucinations, which limits the full potential of LLMs. In this work, we first identify and categorize the common types of hallucinations at each stage in text-to-SQL. We then introduce a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15307","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/2405.15307/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":"2405.15307","created_at":"2026-07-05T08:22:47.554193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15307v1","created_at":"2026-07-05T08:22:47.554193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15307","created_at":"2026-07-05T08:22:47.554193+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDAK5TLMDQQV","created_at":"2026-07-05T08:22:47.554193+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDAK5TLMDQQV2JFS","created_at":"2026-07-05T08:22:47.554193+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDAK5TLM","created_at":"2026-07-05T08:22:47.554193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK","json":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK.json","graph_json":"https://pith.science/api/pith-number/IDAK5TLMDQQV2JFS53N4W6NSJK/graph.json","events_json":"https://pith.science/api/pith-number/IDAK5TLMDQQV2JFS53N4W6NSJK/events.json","paper":"https://pith.science/paper/IDAK5TLM"},"agent_actions":{"view_html":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK","download_json":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK.json","view_paper":"https://pith.science/paper/IDAK5TLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15307&json=true","fetch_graph":"https://pith.science/api/pith-number/IDAK5TLMDQQV2JFS53N4W6NSJK/graph.json","fetch_events":"https://pith.science/api/pith-number/IDAK5TLMDQQV2JFS53N4W6NSJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK/action/storage_attestation","attest_author":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK/action/author_attestation","sign_citation":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK/action/citation_signature","submit_replication":"https://pith.science/pith/IDAK5TLMDQQV2JFS53N4W6NSJK/action/replication_record"}},"created_at":"2026-07-05T08:22:47.554193+00:00","updated_at":"2026-07-05T08:22:47.554193+00:00"}