{"id":"https://openalex.org/W4415013296","doi":null,"title":"Can Large Language Models (LLMs) Describe Pictures Like Children? A Comparative Corpus Study","display_name":"Can Large Language Models (LLMs) Describe Pictures Like Children? A Comparative Corpus Study","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4415013296"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.13769","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13769","pdf_url":"https://arxiv.org/pdf/2508.13769","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.13769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118143166","display_name":"Hanna Woloszyn","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Woloszyn, Hanna","raw_affiliation_strings":["Self-Learning Systems Lab , Faculty of Human Sciences , Department of Special Education and Rehabilitation , Cologne , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Self-Learning Systems Lab , Faculty of Human Sciences , Department of Special Education and Rehabilitation , Cologne , Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058493803","display_name":"Benjamin Gagl","orcid":"https://orcid.org/0000-0002-2339-6293","observed_orcids":["https://orcid.org/0000-0002-2339-6293"]},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gagl, Benjamin","raw_affiliation_strings":["Self-Learning Systems Lab , Faculty of Human Sciences , Department of Special Education and Rehabilitation , Cologne , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Self-Learning Systems Lab , Faculty of Human Sciences , Department of Special Education and Rehabilitation , Cologne , Germany","institution_ids":["https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180923762"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.41819998621940613,"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"}},"topics":[{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.41819998621940613,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.33009999990463257,"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":0.051899999380111694,"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/large-language-models","display_name":"large language models","score":1.0},{"id":"https://openalex.org/keywords/child-language","display_name":"child language","score":0.7940000295639038},{"id":"https://openalex.org/keywords/llm-generated-text","display_name":"LLM-generated text","score":0.8180000185966492},{"id":"https://openalex.org/keywords/child-directed-language","display_name":"child-directed language","score":0.32899999618530273},{"id":"https://openalex.org/keywords/lexical-diversity","display_name":"lexical diversity","score":0.6320000290870667},{"id":"https://openalex.org/keywords/word-frequency","display_name":"word frequency","score":0.8289999961853027},{"id":"https://openalex.org/keywords/part-of-speech-distribution","display_name":"part-of-speech distribution","score":0.7549999952316284},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.9359999895095825},{"id":"https://openalex.org/keywords/multimodal-prompting","display_name":"multimodal prompting","score":0.824999988079071},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.7919999957084656},{"id":"https://openalex.org/keywords/educational-technology","display_name":"educational technology","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5891000032424927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5882999897003174},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5802000164985657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5490999817848206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5461000204086304},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49000000953674316},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3677000105381012},{"id":"https://openalex.org/C89267518","wikidata":"https://www.wikidata.org/wiki/Q179488","display_name":"Psycholinguistics","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C123960582","wikidata":"https://www.wikidata.org/wiki/Q1455196","display_name":"Language education","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C59985594","wikidata":"https://www.wikidata.org/wiki/Q1758140","display_name":"Contrastive linguistics","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C2780790391","wikidata":"https://www.wikidata.org/wiki/Q1149626","display_name":"Written language","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2508.13769","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13769","pdf_url":"https://arxiv.org/pdf/2508.13769","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.13769","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.13769","pdf_url":"https://arxiv.org/pdf/2508.13769","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6164000034332275,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415013296.pdf","grobid_xml":"https://content.openalex.org/works/W4415013296.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494946869","https://openalex.org/W1614298861","https://openalex.org/W1997161938","https://openalex.org/W2076465362","https://openalex.org/W2108997568","https://openalex.org/W2250539671","https://openalex.org/W2493916176","https://openalex.org/W2788784374","https://openalex.org/W2966599707","https://openalex.org/W3030163527","https://openalex.org/W4220761115","https://openalex.org/W4221161695","https://openalex.org/W4309098260","https://openalex.org/W4327810158","https://openalex.org/W4375860407","https://openalex.org/W4384261711","https://openalex.org/W4387847960","https://openalex.org/W4389519222","https://openalex.org/W4390690464","https://openalex.org/W4392560835","https://openalex.org/W4392682363","https://openalex.org/W4399251789","https://openalex.org/W4401043297","https://openalex.org/W4404188231","https://openalex.org/W4405355167","https://openalex.org/W6965760424"],"related_works":["https://openalex.org/W4387847960","https://openalex.org/W4415442932","https://openalex.org/W4389009563","https://openalex.org/W4417282285","https://openalex.org/W7102393447","https://openalex.org/W4405355167","https://openalex.org/W7202341371","https://openalex.org/W7147629014","https://openalex.org/W7222548506","https://openalex.org/W7128519731"],"abstract_inverted_index":{"The":[0,98,159],"role":[1],"of":[2,39,43,134,165,195],"large":[3],"language":[4,31,170,197],"models":[5],"(LLMs)":[6],"in":[7,183,198],"education":[8,187],"is":[9],"increasing,":[10],"yet":[11],"little":[12],"attention":[13],"has":[14],"been":[15],"paid":[16],"to":[17,36,146,153,162],"whether":[18],"LLM-generated":[19,34,102,196],"text":[20,79,145],"resembles":[21],"child":[22,169],"language.":[23],"This":[24],"study":[25],"evaluates":[26],"how":[27,166],"LLMs":[28,167],"replicate":[29,154],"child-like":[30],"by":[32],"comparing":[33],"texts":[35,103],"a":[37,65,74,147],"collection":[38],"German":[40],"children's":[41],"descriptions":[42],"picture":[44,54],"stories.":[45],"We":[46,72],"generated":[47],"two":[48,57,129],"LLM-based":[49],"corpora":[50,130],"using":[51],"the":[52,69,128,132,193],"same":[53],"stories":[55],"and":[56,61,87,92,115,143,156,177,186],"prompt":[58,138],"types:":[59],"zero-shot":[60],"few-shot":[62],"prompts":[63],"specifying":[64],"general":[66],"age":[67],"from":[68],"children":[70,142],"corpus.":[71],"conducted":[73],"comparative":[75],"analysis":[76,121],"across":[77],"psycholinguistic":[78,184],"properties,":[80],"including":[81],"word":[82,88,96],"frequency,":[83],"lexical":[84,155],"richness,":[85],"sentence":[86],"length,":[89],"part-of-speech":[90],"tags,":[91],"semantic":[93,157],"similarity":[94],"with":[95],"embeddings.":[97],"results":[99],"show":[100],"that":[101],"are":[104],"longer":[105],"but":[106,150],"less":[107],"lexically":[108],"rich,":[109],"rely":[110],"more":[111],"on":[112,131],"high-frequency":[113],"words,":[114],"under-represent":[116],"nouns.":[117],"Semantic":[118],"vector":[119],"space":[120],"revealed":[122],"low":[123],"similarity,":[124],"highlighting":[125],"differences":[126],"between":[127,141],"level":[133],"corpus":[135],"semantics.":[136],"Few-shot":[137],"increased":[139],"similarities":[140],"LLM":[144],"minor":[148],"extent,":[149],"still":[151],"failed":[152],"patterns.":[158],"findings":[160],"contribute":[161],"our":[163],"understanding":[164],"approximate":[168],"through":[171],"multimodal":[172],"prompting":[173],"(text":[174],"+":[175],"image)":[176],"give":[178],"insights":[179],"into":[180],"their":[181],"use":[182],"research":[185],"while":[188],"raising":[189],"important":[190],"questions":[191],"about":[192],"appropriateness":[194],"child-directed":[199],"educational":[200],"tools.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}