{"id":"https://openalex.org/W4416701740","doi":"https://doi.org/10.1016/j.caeai.2025.100510","title":"Level-specific feedback generation for scene descriptions via fine-tuning multimodal large language models","display_name":"Level-specific feedback generation for scene descriptions via fine-tuning multimodal large language models","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W4416701740","doi":"https://doi.org/10.1016/j.caeai.2025.100510"},"language":"en","primary_location":{"id":"doi:10.1016/j.caeai.2025.100510","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.caeai.2025.100510","pdf_url":null,"source":{"id":"https://openalex.org/S4210183364","display_name":"Computers and Education Artificial Intelligence","issn_l":"2666-920X","issn":["2666-920X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Education: Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.caeai.2025.100510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101705597","display_name":"Zhiwei Xie","orcid":"https://orcid.org/0009-0009-9018-2891"},"institutions":[{"id":"https://openalex.org/I4210086892","display_name":"Education University of Hong Kong","ror":"https://ror.org/000t0f062","country_code":"HK","type":"education","lineage":["https://openalex.org/I4210086892"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiwei Xie","raw_affiliation_strings":["Department of Mathematics and Information Technology, The Education University of Hong Kong, 10 Lo Ping Road, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Information Technology, The Education University of Hong Kong, 10 Lo Ping Road, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210086892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047023625","display_name":"Tse-Tin Chan","orcid":"https://orcid.org/0000-0001-9235-7813"},"institutions":[{"id":"https://openalex.org/I4210086892","display_name":"Education University of Hong Kong","ror":"https://ror.org/000t0f062","country_code":"HK","type":"education","lineage":["https://openalex.org/I4210086892"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tse-Tin Chan","raw_affiliation_strings":["Department of Mathematics and Information Technology, The Education University of Hong Kong, 10 Lo Ping Road, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Information Technology, The Education University of Hong Kong, 10 Lo Ping Road, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210086892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018396769","display_name":"Philip L. H. Yu","orcid":"https://orcid.org/0000-0002-9449-0420"},"institutions":[{"id":"https://openalex.org/I4210086892","display_name":"Education University of Hong Kong","ror":"https://ror.org/000t0f062","country_code":"HK","type":"education","lineage":["https://openalex.org/I4210086892"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Philip L.H. Yu","raw_affiliation_strings":["Department of Mathematics and Information Technology, The Education University of Hong Kong, 10 Lo Ping Road, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-9449-0420","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Information Technology, The Education University of Hong Kong, 10 Lo Ping Road, Hong Kong SAR, China","institution_ids":["https://openalex.org/I4210086892"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5018396769"],"corresponding_institution_ids":["https://openalex.org/I4210086892"],"apc_list":{"value":1800,"currency":"USD","value_usd":1800},"apc_paid":{"value":1800,"currency":"USD","value_usd":1800},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33037157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"100510","last_page":"100510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4426000118255615,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4426000118255615,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.14800000190734863,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.10509999841451645,"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/hallucinating","display_name":"Hallucinating","score":0.7864000201225281},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5644000172615051},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5618000030517578},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.539900004863739},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5264000296592712},{"id":"https://openalex.org/keywords/situational-ethics","display_name":"Situational ethics","score":0.46799999475479126},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.439300000667572}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.7864000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483000159263611},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5618000030517578},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C9114305","wikidata":"https://www.wikidata.org/wiki/Q1428317","display_name":"Situational ethics","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45080000162124634},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2781265381","wikidata":"https://www.wikidata.org/wiki/Q5710255","display_name":"Helpfulness","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.caeai.2025.100510","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.caeai.2025.100510","pdf_url":null,"source":{"id":"https://openalex.org/S4210183364","display_name":"Computers and Education Artificial Intelligence","issn_l":"2666-920X","issn":["2666-920X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Education: Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0a1c44f422de49eda8f3906b7036e17b","is_oa":true,"landing_page_url":"https://doaj.org/article/0a1c44f422de49eda8f3906b7036e17b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers and Education: Artificial Intelligence, Vol 9, Iss , Pp 100510- (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.caeai.2025.100510","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.caeai.2025.100510","pdf_url":null,"source":{"id":"https://openalex.org/S4210183364","display_name":"Computers and Education Artificial Intelligence","issn_l":"2666-920X","issn":["2666-920X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Education: Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"},{"id":"https://openalex.org/F4320322867","display_name":"Hong Kong Institute of Education","ror":"https://ror.org/000t0f062"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1970209023","https://openalex.org/W2003502612","https://openalex.org/W2051339053","https://openalex.org/W2059874629","https://openalex.org/W2100588183","https://openalex.org/W2101174054","https://openalex.org/W2130736456","https://openalex.org/W2135995390","https://openalex.org/W2142995122","https://openalex.org/W2170058424","https://openalex.org/W2185175083","https://openalex.org/W2560140854","https://openalex.org/W2567547739","https://openalex.org/W2619383789","https://openalex.org/W2797679147","https://openalex.org/W2923646821","https://openalex.org/W2963115613","https://openalex.org/W2970641574","https://openalex.org/W3035877907","https://openalex.org/W3089635816","https://openalex.org/W3161448525","https://openalex.org/W3198843646","https://openalex.org/W4284896011","https://openalex.org/W4309259993","https://openalex.org/W4309674289","https://openalex.org/W4310154890","https://openalex.org/W4313422842","https://openalex.org/W4384662964","https://openalex.org/W4389089964","https://openalex.org/W4391094120","https://openalex.org/W4396687678","https://openalex.org/W4399693573","https://openalex.org/W4401110170","https://openalex.org/W4402727764","https://openalex.org/W4404356490","https://openalex.org/W4404612934"],"related_works":[],"abstract_inverted_index":{"Scene":[0],"description":[1,49,75,162],"tasks":[2,50],"effectively":[3],"enhance":[4],"students'":[5,59],"English":[6,96],"writing":[7,171],"skills":[8],"in":[9,41,141,156,173,207],"contextual":[10],"settings,":[11],"facilitating":[12],"the":[13,89,132,151,165],"establishment":[14],"of":[15,153],"authentic":[16],"situational":[17],"connections.":[18],"However,":[19],"evaluating":[20],"descriptive":[21],"quality":[22],"and":[23,93,119,125,195],"providing":[24,157],"accurate,":[25],"level-appropriate":[26],"feedback":[27,46,71,142,159,208],"present":[28],"significant":[29,201],"challenges.":[30],"Although":[31],"Multimodal":[32],"Large":[33],"Language":[34],"Models":[35],"(MLLMs)":[36],"have":[37],"demonstrated":[38],"strong":[39],"capabilities":[40],"vision-language":[42],"tasks,":[43,163],"their":[44],"generated":[45],"for":[47,58,73,160,167,186],"scene":[48,74,161,187],"often":[51],"remains":[52],"generic.":[53],"It":[54],"fails":[55],"to":[56,109,182],"account":[57],"educational":[60,104,138,174,193],"stages.":[61],"To":[62],"address":[63],"this":[64,117],"limitation,":[65],"we":[66],"construct":[67],"a":[68,113],"novel":[69],"level-specific":[70,158,184],"dataset":[72,78,118],"tasks.":[76],"This":[77],"is":[79],"constructed":[80],"using":[81],"GPT-4o":[82],"with":[83],"Retrieval-Augmented":[84],"Generation":[85],"(RAG),":[86],"guided":[87],"by":[88],"Hong":[90],"Kong":[91],"primary":[92],"secondary":[94],"school":[95],"word":[97],"lists,":[98],"which":[99],"categorize":[100],"vocabulary":[101],"into":[102],"four":[103],"stages":[105,107],"(key":[106],"1":[108],"4).":[110],"We":[111],"fine-tuned":[112,134,154],"designed":[114],"MLLM":[115,135,155,191],"on":[116],"evaluated":[120],"its":[121],"performance":[122,202],"against":[123],"open-source":[124],"closed-source":[126],"baselines.":[127],"Experimental":[128],"results":[129],"demonstrate":[130],"that":[131],"proposed":[133],"significantly":[136],"enhances":[137],"stage":[139],"relevance":[140,194],"generation":[143],"while":[144],"reducing":[145],"hallucinated":[146,197],"content.":[147,198],"These":[148],"findings":[149],"substantiate":[150],"efficacy":[152],"advancing":[164],"potential":[166],"more":[168],"adaptive":[169],"AI-assisted":[170],"support":[172],"contexts.":[175],"\u2022":[176,179,189,199],"Highlights":[177],"(3-5)":[178],"Fine-tuning":[180],"MLLMs":[181],"generate":[183],"feedbacks":[185],"descriptions.":[188],"Fine-tuned":[190],"improves":[192],"reduces":[196],"Demonstrated":[200],"enhancement":[203],"over":[204],"baseline":[205],"models":[206],"generation.":[209]},"counts_by_year":[],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-11-27T00:00:00"}