{"id":"https://openalex.org/W4412889251","doi":"https://doi.org/10.18653/v1/2025.bea-1.22","title":"Challenges for AI in Multimodal STEM Assessments: a Human-AI Comparison","display_name":"Challenges for AI in Multimodal STEM Assessments: a Human-AI Comparison","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889251","doi":"https://doi.org/10.18653/v1/2025.bea-1.22"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.bea-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.22","pdf_url":"https://aclanthology.org/2025.bea-1.22.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.bea-1.22.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181657","display_name":"Aymeric de Chillaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aymeric de Chillaz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111117835","display_name":"Anna Sotnikova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna Sotnikova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056251462","display_name":"Patrick Jermann","orcid":"https://orcid.org/0000-0001-9199-2831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Jermann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088410008","display_name":"Antoine Bosselut","orcid":"https://orcid.org/0000-0001-8968-9649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Bosselut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.26327789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13482","display_name":"Engineering Education and Technology","score":0.6219000220298767,"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"}},"topics":[{"id":"https://openalex.org/T13482","display_name":"Engineering Education and Technology","score":0.6219000220298767,"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"}},{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.6100999712944031,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.5350000262260437,"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/computer-science","display_name":"Computer science","score":0.5191687345504761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3776904046535492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5191687345504761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3776904046535492}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.bea-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.22","pdf_url":"https://aclanthology.org/2025.bea-1.22.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"},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/257690","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/257690","pdf_url":"https://infoscience.epfl.ch/bitstreams/292eee14-050b-4df6-bf83-f55c6ce7e1d8/download","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.bea-1.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.bea-1.22","pdf_url":"https://aclanthology.org/2025.bea-1.22.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":[{"id":"https://openalex.org/G3056497733","display_name":null,"funder_award_id":"215390","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8503654337","display_name":null,"funder_award_id":"PFFS-21-29","funder_id":"https://openalex.org/F4320327931","funder_display_name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320327931","display_name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","ror":"https://ror.org/05a2bhn71"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889251.pdf","grobid_xml":"https://content.openalex.org/works/W4412889251.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Generative":[0],"AI":[1,64,107,125,156],"systems":[2,157],"have":[3],"rapidly":[4],"advanced,":[5],"with":[6,45,73],"multimodal":[7],"input":[8],"capabilities":[9],"enabling":[10],"reasoning":[11],"beyond":[12],"text-based":[13],"tasks.In":[14],"education,":[15],"these":[16,31,60],"advancements":[17],"could":[18],"influence":[19],"assessment":[20],"design":[21,145],"and":[22,28,54,133],"question":[23,55,118,134,144],"answering,":[24],"presenting":[25],"both":[26,130],"opportunities":[27],"challenges.To":[29],"investigate":[30],"effects,":[32],"we":[33,136],"introduce":[34],"a":[35],"highquality":[36],"dataset":[37],"of":[38,82,96],"201":[39],"university-level":[40],"STEM":[41],"questions,":[42],"manually":[43],"annotated":[44],"features":[46,61,119,152],"such":[47],"as":[48],"image":[49],"type,":[50],"role,":[51],"problem":[52],"complexity,":[53],"format.Our":[56],"study":[57],"analyzes":[58],"how":[59,143],"affect":[62],"generative":[63],"performance":[65,114,126],"compared":[66],"to":[67,79,129],"students.We":[68],"evaluate":[69],"four":[70],"model":[71,90],"families":[72],"five":[74],"prompting":[75],"strategies,":[76],"comparing":[77],"results":[78],"the":[80,88,97,160],"average":[81,94],"546":[83],"student":[84],"responses":[85],"per":[86],"question.Although":[87],"best":[89],"correctly":[91],"answers":[92],"on":[93,108],"58.5%":[95],"questions":[98,109],"using":[99],"majority":[100],"vote":[101],"aggregation,":[102],"human":[103,113],"participants":[104],"consistently":[105],"outperform":[106],"involving":[110],"visual":[111],"components.Interestingly,":[112],"remains":[115],"stable":[116],"across":[117],"but":[120],"varies":[121],"by":[122,150],"subject,":[123],"whereas":[124],"is":[127],"susceptible":[128],"subject":[131],"matter":[132],"features.Finally,":[135],"provide":[137],"actionable":[138],"insights":[139],"for":[140,163],"educators,":[141],"demonstrating":[142],"can":[146],"enhance":[147],"academic":[148],"integrity":[149],"leveraging":[151],"that":[153],"challenge":[154],"current":[155],"without":[158],"increasing":[159],"cognitive":[161],"burden":[162],"students.":[164]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}