{"id":"https://openalex.org/W7166805129","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.20","title":"Mixed-Policy GRPO for Text-to-SQL with Off-Policy Data Generation","display_name":"Mixed-Policy GRPO for Text-to-SQL with Off-Policy Data Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166805129","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.20"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.surgellm-1.20","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.surgellm-1.20","pdf_url":"https://aclanthology.org/2026.surgellm-1.20.pdf","source":{"id":"https://openalex.org/S7407121045","display_name":"Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.surgellm-1.20.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087714040","display_name":"Marko Sterbentz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marko Sterbentz","raw_affiliation_strings":["Northwestern University \u2663 IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University \u2663 IBM Research","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019777435","display_name":"Michael Glass","orcid":"https://orcid.org/0009-0000-1505-4667","observed_orcids":["https://orcid.org/0009-0000-1505-4667"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Glass","raw_affiliation_strings":["Northwestern University \u2663 IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University \u2663 IBM Research","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011485086","display_name":"Nhan H. Pham","orcid":"https://orcid.org/0000-0002-4490-8649","observed_orcids":["https://orcid.org/0000-0002-4490-8649"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nhan H Pham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052501780","display_name":"Dharmashankar Subramanian","orcid":"https://orcid.org/0000-0002-1990-7740","observed_orcids":["https://orcid.org/0000-0002-1990-7740"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dharmashankar Subramanian","raw_affiliation_strings":["Northwestern University \u2663 IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University \u2663 IBM Research","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114000097","display_name":"Kristian J. Hammond","orcid":"https://orcid.org/0000-0002-4579-6685","observed_orcids":["https://orcid.org/0000-0002-4579-6685"]},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristian J Hammond","raw_affiliation_strings":["Northwestern University \u2663 IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University \u2663 IBM Research","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43912945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2337999939918518,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2337999939918518,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1808999925851822,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.12729999423027039,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-sql","display_name":"text-to-SQL","score":0.9259999990463257},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.5450000166893005},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.38199999928474426},{"id":"https://openalex.org/keywords/structured-data-generation","display_name":"structured data generation","score":0.3610000014305115},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6909999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48429998755455017},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C3018907156","wikidata":"https://www.wikidata.org/wiki/Q7785058","display_name":"Third generation","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2313999980688095},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.22849999368190765},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.22769999504089355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22220000624656677},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2151000052690506}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.surgellm-1.20","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.surgellm-1.20","pdf_url":"https://aclanthology.org/2026.surgellm-1.20.pdf","source":{"id":"https://openalex.org/S7407121045","display_name":"Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.surgellm-1.20","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.surgellm-1.20","pdf_url":"https://aclanthology.org/2026.surgellm-1.20.pdf","source":{"id":"https://openalex.org/S7407121045","display_name":"Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166805129.pdf","grobid_xml":"https://content.openalex.org/works/W7166805129.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385565008","https://openalex.org/W3093819145","https://openalex.org/W4403344290","https://openalex.org/W4402683779","https://openalex.org/W4412945149","https://openalex.org/W4389519829","https://openalex.org/W4388639106","https://openalex.org/W7138053346","https://openalex.org/W4402670079","https://openalex.org/W4416037367"],"abstract_inverted_index":{"Marko":[0],"Sterbentz,":[1],"Michael":[2],"Glass,":[3],"Nhan":[4],"H":[5],"Pham,":[6],"Dharmashankar":[7],"Subramanian,":[8],"Kristian":[9],"J":[10],"Hammond.":[11],"Proceedings":[12],"of":[13],"the":[14,24],"First":[15],"Workshop":[16],"on":[17],"Structured":[18],"Understanding,":[19],"Retrieval,":[20],"and":[21],"Generation":[22],"in":[23],"LLM":[25],"Era":[26],"(SURGeLLM":[27],"2026).":[28],"2026.":[29]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}
