{"id":"https://openalex.org/W4417294977","doi":"https://doi.org/10.1145/3785022.3785100","title":"Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models","display_name":"Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models","publication_year":2026,"publication_date":"2026-04-25","ids":{"openalex":"https://openalex.org/W4417294977","doi":"https://doi.org/10.1145/3785022.3785100"},"language":null,"primary_location":{"id":"doi:10.1145/3785022.3785100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785022.3785100","pdf_url":null,"source":null,"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 LAK26: 16th International Learning Analytics and Knowledge Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3785022.3785100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102654525","display_name":"Yumou Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yumou Wei","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0002-1364-8300","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060576109","display_name":"John Stamper","orcid":"https://orcid.org/0000-0002-2291-1468"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Stamper","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-2291-1468","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026875699","display_name":"Paulo F. Carvalho","orcid":"https://orcid.org/0000-0002-0449-3733"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paulo F. Carvalho","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-0449-3733","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102654525"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01308322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.489300012588501,"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/T10028","display_name":"Topic Modeling","score":0.489300012588501,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.13830000162124634,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.08630000054836273,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/pipeline","display_name":"Pipeline (software)","score":0.7556999921798706},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.7167999744415283},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6766999959945679},{"id":"https://openalex.org/keywords/expansive","display_name":"Expansive","score":0.6136999726295471},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5095999836921692},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.42829999327659607},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.38260000944137573},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36820000410079956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742000222206116},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7556999921798706},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.7167999744415283},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6766999959945679},{"id":"https://openalex.org/C2780502288","wikidata":"https://www.wikidata.org/wiki/Q28838156","display_name":"Expansive","level":3,"score":0.6136999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014999747276306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5174000263214111},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3952000141143799},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3785022.3785100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785022.3785100","pdf_url":null,"source":null,"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 LAK26: 16th International Learning Analytics and Knowledge Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.10110","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10110","pdf_url":"https://arxiv.org/pdf/2512.10110","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.10110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.10110","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3785022.3785100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3785022.3785100","pdf_url":null,"source":null,"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 LAK26: 16th International Learning Analytics and Knowledge Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2220500170","display_name":null,"funder_award_id":"2418656","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7482023331","display_name":null,"funder_award_id":"2301130","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,28,80],"explore":[1],"the":[2,17,38,42,91,101,104,114,125],"use":[3,19],"of":[4,20,46,66,103],"small":[5],"language":[6,96],"models":[7],"(SLMs)":[8],"for":[9],"automatic":[10],"question":[11,32],"generation":[12,33,40,61],"as":[13],"a":[14,30,53,94,143],"complement":[15],"to":[16,48,62,99],"prevalent":[18],"their":[21],"large":[22,95],"counterparts":[23],"in":[24],"learning":[25,127],"analytics":[26],"research.":[27],"present":[29],"novel":[31,77],"pipeline":[34,57,145],"that":[35,113,132,146],"leverages":[36,147],"both":[37],"text":[39],"and":[41,69,90,120],"probabilistic":[43,78],"reasoning":[44],"abilities":[45],"SLMs":[47],"generate":[49,137],"high-quality":[50,138],"questions.":[51,106],"Adopting":[52],"\u201cgenerate-then-validate\u201d":[54],"strategy,":[55],"our":[56],"first":[58],"performs":[59],"expansive":[60],"create":[63],"an":[64,133],"abundance":[65],"candidate":[67],"questions":[68,116,139],"refine":[70],"them":[71],"through":[72],"selective":[73],"validation":[74],"based":[75],"on":[76],"reasoning.":[79],"conducted":[81],"two":[82],"evaluation":[83],"studies,":[84],"one":[85],"with":[86,93,124],"seven":[87],"human":[88],"experts":[89],"other":[92],"model":[97],"(LLM),":[98],"assess":[100],"quality":[102],"generated":[105,115],"Most":[107],"judges":[108],"(humans":[109],"or":[110],"LLMs)":[111],"agreed":[112],"had":[117],"clear":[118],"answers":[119],"generally":[121],"aligned":[122],"well":[123],"intended":[126],"objectives.":[128],"Our":[129],"findings":[130],"suggest":[131],"SLM":[134],"can":[135],"effectively":[136],"when":[140],"guided":[141],"by":[142],"well-designed":[144],"its":[148],"strengths.":[149]},"counts_by_year":[],"updated_date":"2026-04-27T06:02:13.124806","created_date":"2025-12-13T00:00:00"}