{"id":"https://openalex.org/W7152230372","doi":"https://doi.org/10.48550/arxiv.2604.05005","title":"EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content","display_name":"EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7152230372","doi":"https://doi.org/10.48550/arxiv.2604.05005"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.05005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05005","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.05005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089126072","display_name":"Shilei Bi","orcid":"https://orcid.org/0009-0001-1257-1826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bi, Shuzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133196299","display_name":"Mingzi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Mingzi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133190939","display_name":"Zhuoxuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhuoxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133157850","display_name":"Xiaolong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaolong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049950372","display_name":"Keqian Li","orcid":"https://orcid.org/0009-0002-5956-3038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Keqian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133201596","display_name":"Aimin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Aimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9671000242233276,"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":0.9671000242233276,"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/T10028","display_name":"Topic Modeling","score":0.007300000172108412,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0019000000320374966,"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/rubric","display_name":"Rubric","score":0.8379999995231628},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7322999835014343},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6654999852180481},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.640500009059906},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5311999917030334},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4438000023365021}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.8379999995231628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576000094413757},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7322999835014343},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6654999852180481},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.640500009059906},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4945000112056732},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4634999930858612},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31200000643730164},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.05005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05005","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.05005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05005","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8520101308822632}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"are":[3],"increasingly":[4],"used":[5],"as":[6],"educational":[7,13],"assistants,":[8],"yet":[9],"evaluation":[10,91,144],"of":[11,105],"their":[12],"capabilities":[14],"remains":[15],"concentrated":[16],"on":[17,55,160],"question-answering":[18],"and":[19,72,88,101],"tutoring":[20],"tasks.":[21],"A":[22],"critical":[23],"gap":[24],"exists":[25],"for":[26,52,60,152],"multimedia":[27,95],"instructional":[28],"content":[29],"generation":[30,59,78],"--":[31],"the":[32,123],"ability":[33],"to":[34,83],"produce":[35],"coherent,":[36],"diagram-rich":[37],"explanations":[38],"that":[39],"combine":[40],"geometrically":[41],"accurate":[42],"visuals":[43],"with":[44,80,145],"step-by-step":[45],"reasoning.":[46],"We":[47],"present":[48],"EduIllustrate,":[49],"a":[50,76,109],"benchmark":[51,65],"evaluating":[53],"LLMs":[54,107],"interleaved":[56],"text-diagram":[57],"explanation":[58],"K-12":[61],"STEM":[62],"problems.":[63],"The":[64],"comprises":[66],"230":[67],"problems":[68],"spanning":[69],"five":[70],"subjects":[71],"three":[73],"grade":[74],"levels,":[75],"standardized":[77],"protocol":[79],"sequential":[81,132],"anchoring":[82,133],"enforce":[84],"cross-diagram":[85],"visual":[86,102,162],"consistency,":[87],"an":[89],"8-dimension":[90],"rubric":[92],"grounded":[93],"in":[94],"learning":[96],"theory":[97],"covering":[98],"both":[99],"text":[100],"quality.":[103],"Evaluation":[104],"ten":[106],"reveals":[108],"wide":[110],"performance":[111],"spread:":[112],"Gemini":[113],"3.0":[114],"Pro":[115],"Preview":[116],"leads":[117],"at":[118,127,139],"87.8\\%,":[119],"while":[120,157],"Kimi-K2.5":[121],"achieves":[122],"best":[124],"cost-efficiency":[125],"(80.8\\%":[126],"\\\\$0.12/problem).":[128],"Workflow":[129],"ablation":[130],"confirms":[131],"improves":[134],"Visual":[135],"Consistency":[136],"by":[137],"13\\%":[138],"94\\%":[140],"lower":[141],"cost.":[142],"Human":[143],"20":[146],"expert":[147],"raters":[148],"validates":[149],"LLM-as-judge":[150],"reliability":[151],"objective":[153],"dimensions":[154],"($\u03c1\\geq":[155],"0.83$)":[156],"revealing":[158],"limitations":[159],"subjective":[161],"assessment.":[163]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-09T00:00:00"}