{"id":"https://openalex.org/W4412889215","doi":"https://doi.org/10.18653/v1/2025.bea-1.11","title":"Is Lunch Free Yet? Overcoming the Cold-Start Problem in Supervised Content Scoring using Zero-Shot LLM-Generated Training Data","display_name":"Is Lunch Free Yet? Overcoming the Cold-Start Problem in Supervised Content Scoring using Zero-Shot LLM-Generated Training Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889215","doi":"https://doi.org/10.18653/v1/2025.bea-1.11"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.11","pdf_url":"https://aclanthology.org/2025.bea-1.11.pdf","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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.bea-1.11.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038630453","display_name":"Marie Bexte","orcid":"https://orcid.org/0000-0002-7329-2548"},"institutions":[{"id":"https://openalex.org/I120691247","display_name":"FernUniversit\u00e4t in Hagen","ror":"https://ror.org/04tkkr536","country_code":"DE","type":"education","lineage":["https://openalex.org/I120691247"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marie Bexte","raw_affiliation_strings":["Center of Advanced Technology for Assisted Learning and Predictive Analytics FernUniversitt in Hagen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Advanced Technology for Assisted Learning and Predictive Analytics FernUniversitt in Hagen , Germany","institution_ids":["https://openalex.org/I120691247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072459546","display_name":"Torsten Zesch","orcid":"https://orcid.org/0000-0002-9678-3825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Torsten Zesch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":0.1457223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9391000270843506,"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":0.9391000270843506,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.925000011920929,"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/shot","display_name":"Shot (pellet)","score":0.6765295267105103},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6725583672523499},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5904021859169006},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5837646722793579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5813915133476257},{"id":"https://openalex.org/keywords/cold-start","display_name":"Cold start (automotive)","score":0.5482171773910522},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5227941870689392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42443180084228516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22088244557380676},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08255216479301453},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.06254801154136658},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05919131636619568}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6765295267105103},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6725583672523499},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5904021859169006},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5837646722793579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5813915133476257},{"id":"https://openalex.org/C2778956030","wikidata":"https://www.wikidata.org/wiki/Q5142477","display_name":"Cold start (automotive)","level":2,"score":0.5482171773910522},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5227941870689392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42443180084228516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22088244557380676},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08255216479301453},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.06254801154136658},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05919131636619568},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.11","pdf_url":"https://aclanthology.org/2025.bea-1.11.pdf","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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.11","pdf_url":"https://aclanthology.org/2025.bea-1.11.pdf","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 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889215.pdf","grobid_xml":"https://content.openalex.org/works/W4412889215.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2053154970"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"In":[0],"this":[1,42],"work,":[2],"we":[3,30,77],"assess":[4],"the":[5,25,60,74,89,95,105,110,119,123,139,156,163],"potential":[6],"of":[7,21,35,62,66,88,143,153,159],"using":[8],"synthetic":[9,144],"data":[10,23,53,68,84,91,124],"to":[11,48,116,118],"train":[12,31],"models":[13,36,81,97,102,129],"for":[14,24],"content":[15],"scoring.We":[16],"generate":[17],"a":[18,135,148],"parallel":[19],"corpus":[20],"LLMgenerated":[22],"SRA":[26],"dataset.In":[27],"our":[28],"experiments,":[29],"three":[32],"different":[33],"kinds":[34],"(Logistic":[37],"Regression,":[38],"BERT,":[39],"SBERT)":[40],"with":[41,92],"data,":[43,107],"examining":[44],"their":[45],"respective":[46],"ability":[47],"bridge":[49],"between":[50],"generated":[51],"training":[52,67,80,154],"and":[54],"student-authored":[55],"test":[56,90],"data.We":[57],"also":[58],"explore":[59],"effects":[61],"generating":[63],"larger":[64],"volumes":[65],"than":[69,101],"what":[70],"is":[71,125],"available":[72,161],"in":[73,162],"original":[75,106,164],"dataset.Overall,":[76],"find":[78],"that":[79,150],"from":[82,133],"LLM-generated":[83,111],"outperforms":[85],"zero-shot":[86],"scoring":[87,137],"an":[93],"LLM.Still,":[94],"fine-tuned":[96],"perform":[98],"much":[99],"worse":[100],"trained":[103,132],"on":[104,155],"largely":[108],"because":[109],"answers":[112,145,160],"often":[113],"do":[114],"not":[115],"conform":[117],"desired":[120],"labels.However,":[121],"once":[122],"manually":[126],"relabeled,":[127],"competitive":[128],"can":[130],"be":[131],"it.With":[134],"similarity-based":[136],"approach,":[138],"relabeled":[140],"(larger)":[141],"amount":[142,158],"consistently":[146],"yields":[147],"model":[149],"surpasses":[151],"performance":[152],"(limited)":[157],"dataset.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}