{"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/benchmarking-and-improving-text-to-sql","title":"Benchmarking and Improving Text-to-SQL Generation under Ambiguity","arxiv_id":"2310.13659","date":"2023-10-20","proceeding":null,"authors":["Adithya Bhaskar","Tushar Tomar","Ashutosh Sathe","Sunita Sarawagi"],"abstract":"Research in Text-to-SQL conversion has been largely benchmarked against datasets where each text query corresponds to one correct SQL. However, natural language queries over real-life databases frequently involve significant ambiguity about the intended SQL due to overlapping schema names and multiple confusing relationship paths. To bridge this gap, we develop a novel benchmark called AmbiQT with over 3000 examples where each text is interpretable as two plausible SQLs due to lexical and/or structural ambiguity. When faced with ambiguity, an ideal top-$k$ decoder should generate all valid interpretations for possible disambiguation by the user. We evaluate several Text-to-SQL systems and decoding algorithms, including those employing state-of-the-art LLMs, and find them to be far from this ideal. The primary reason is that the prevalent beam search algorithm and its variants, treat SQL queries as a string and produce unhelpful token-level diversity in the top-$k$. We propose LogicalBeam, a new decoding algorithm that navigates the SQL logic space using a blend of plan-based template generation and constrained infilling. Counterfactually generated plans diversify templates while in-filling with a beam-search that branches solely on schema names provides value diversity. LogicalBeam is up to $2.5$ times more effective than state-of-the-art models at generating all candidate SQLs in the top-$k$ ranked outputs. It also enhances the top-$5$ Exact and Execution Match Accuracies on SPIDER and Kaggle DBQA.","url_abs":"https://arxiv.org/abs/2310.13659v1","url_pdf":"https://arxiv.org/pdf/2310.13659v1.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":"benchmarking-and-improving-text-to-sql","repo_url":"https://github.com/testzer0/ambiqt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"text-to-sql","task_name":"Text to SQL"},{"task_slug":"text-to-sql","task_name":"Text-To-SQL"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.13659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13659"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/testzer0/ambiqt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/testzer0/AmbiQT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":12,"unverified":5},"by_repo_kind":{"official":{"samples":17,"ran":12,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0ca547f553ddb65d","entry":"disallowed","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/logicalbeam/ablation_direct.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/logicalbeam/ablation_direct.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ca547f553ddb65d"}},{"code_sha256_prefix":"d3bdc5e617b7e466","entry":"extract_tables_and_columns","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/logicalbeam/ablation_direct.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/logicalbeam/ablation_direct.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3bdc5e617b7e466"}},{"code_sha256_prefix":"180f6cfb0b94cda6","entry":"get_col_mappings","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/data.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"180f6cfb0b94cda6"}},{"code_sha256_prefix":"a29ff82a4708e5c7","entry":"get_output_with_prefix","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/logicalbeam/template_gen.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/logicalbeam/template_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a29ff82a4708e5c7"}},{"code_sha256_prefix":"b0dc867bb550c2d7","entry":"get_selections","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/collate.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/collate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0dc867bb550c2d7"}},{"code_sha256_prefix":"b724cc2d4066a429","entry":"is_commonword","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/content.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/content.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b724cc2d4066a429"}},{"code_sha256_prefix":"f39fdc1ce6cffe08","entry":"is_number","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/content.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/content.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f39fdc1ce6cffe08"}},{"code_sha256_prefix":"d56a1f9221823a48","entry":"is_stopword","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/content.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/content.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d56a1f9221823a48"}},{"code_sha256_prefix":"83fb78ab0d26fa54","entry":"lower","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/collate.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/collate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83fb78ab0d26fa54"}},{"code_sha256_prefix":"56def8190912ab3f","entry":"normalize_spaces","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/sql.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/sql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56def8190912ab3f"}},{"code_sha256_prefix":"f146bec5afa35b8d","entry":"normalize_sql","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/collate.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/collate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f146bec5afa35b8d"}},{"code_sha256_prefix":"4ff91e232c45be1a","entry":"try_extract_json","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/chatgpt/prompter.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/chatgpt/prompter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ff91e232c45be1a"}},{"code_sha256_prefix":"b90b6e1db0a2c350","entry":"get_model_picard","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/model_utils.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b90b6e1db0a2c350"}},{"code_sha256_prefix":"f988bbea8a36c875","entry":"get_reply","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/chatgpt/helper.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/chatgpt/helper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f988bbea8a36c875"}},{"code_sha256_prefix":"73bf0aed972d0f6c","entry":"get_reply_with_retries","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/chatgpt/helper.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/chatgpt/helper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73bf0aed972d0f6c"}},{"code_sha256_prefix":"b2cd044e4edcf9d1","entry":"load_spider","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/data.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2cd044e4edcf9d1"}},{"code_sha256_prefix":"7b30094e3a706d3f","entry":"to_device_multiple","repo":"testzer0/AmbiQT","repo_kind":"official","path":"src/utils/model_utils.py","file_url":"https://github.com/testzer0/AmbiQT/blob/HEAD/src/utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b30094e3a706d3f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}