{"id":"https://openalex.org/W4403798947","doi":"https://doi.org/10.1145/3649409.3691083","title":"ASAG2024: A Combined Benchmark for Short Answer Grading","display_name":"ASAG2024: A Combined Benchmark for Short Answer Grading","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4403798947","doi":"https://doi.org/10.1145/3649409.3691083"},"language":"en","primary_location":{"id":"doi:10.1145/3649409.3691083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649409.3691083","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649409.3691083?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM Virtual Global Computing Education Conference V. 2","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3649409.3691083?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"G\u00e9r\u00f4me Meyer","orcid":"https://orcid.org/0009-0001-6007-4832"},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"G\u00e9r\u00f4me Meyer","raw_affiliation_strings":["Zurich University of Applied Sciences, Winterthur, Switzerland"],"raw_orcid":"https://orcid.org/0009-0001-6007-4832","affiliations":[{"raw_affiliation_string":"Zurich University of Applied Sciences, Winterthur, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Philip Breuer","orcid":"https://orcid.org/0009-0000-5736-695X"},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philip Breuer","raw_affiliation_strings":["Zurich University of Applied Sciences, Winterthur, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-5736-695X","affiliations":[{"raw_affiliation_string":"Zurich University of Applied Sciences, Winterthur, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010965443","display_name":"Jonathan F\u00fcrst","orcid":"https://orcid.org/0000-0002-4062-1827"},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jonathan F\u00fcrst","raw_affiliation_strings":["Zurich University of Applied Sciences, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4062-1827","affiliations":[{"raw_affiliation_string":"Zurich University of Applied Sciences, Zurich, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I858936495"],"apc_list":null,"apc_paid":null,"fwci":7.9935,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97393837,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"322","last_page":"323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10959","display_name":"Student Assessment and Feedback","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10959","display_name":"Student Assessment and Feedback","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9778000116348267,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9764999747276306,"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/grading","display_name":"Grading (engineering)","score":0.8921793699264526},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.8579063415527344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6736558079719543},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4868270754814148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48342692852020264},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47828778624534607},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4778729975223541},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3792528808116913},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32271814346313477},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16450726985931396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14761754870414734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12958166003227234}],"concepts":[{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.8921793699264526},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8579063415527344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736558079719543},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4868270754814148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48342692852020264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47828778624534607},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4778729975223541},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3792528808116913},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32271814346313477},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16450726985931396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14761754870414734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12958166003227234},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3649409.3691083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649409.3691083","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649409.3691083?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM Virtual Global Computing Education Conference V. 2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.18596","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18596","pdf_url":"https://arxiv.org/pdf/2409.18596","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:digitalcollection.zhaw.ch:11475/32080","is_oa":true,"landing_page_url":"https://hdl.handle.net/11475/32080","pdf_url":null,"source":{"id":"https://openalex.org/S4306401810","display_name":"Z\u00fcrcher Hochschule f\u00fcr Angewandte Wissenschaften digital collection (Zurich University of Applied Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200744771","host_organization_name":"ZHAW Zurich University of Applied Sciences","host_organization_lineage":["https://openalex.org/I200744771"],"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":"Text"}],"best_oa_location":{"id":"doi:10.1145/3649409.3691083","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649409.3691083","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649409.3691083?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM Virtual Global Computing Education Conference V. 2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403798947.pdf","grobid_xml":"https://content.openalex.org/works/W4403798947.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1607035479","https://openalex.org/W1967082761","https://openalex.org/W2123159101","https://openalex.org/W2899575547","https://openalex.org/W3125048963","https://openalex.org/W4285178525"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W2388888344"],"abstract_inverted_index":{"Open-ended":[0],"questions":[1,10,20],"test":[2],"a":[3,14,121,132],"more":[4],"thorough":[5],"understanding":[6],"compared":[7],"to":[8,23,27,35,49,81,105],"closed-ended":[9],"and":[11,25,61,75,124],"are":[12,21,149],"often":[13],"preferred":[15],"assessment":[16],"method.":[17],"However,":[18],"open-ended":[19],"tedious":[22],"grade":[24],"subject":[26],"personal":[28],"bias.":[29],"Therefore,":[30],"there":[31,63],"have":[32],"been":[33],"efforts":[34],"speed":[36],"up":[37,157],"the":[38,83,101,107],"grading":[39,68,73,88,111,118,125],"process":[40],"through":[41],"automation.":[42],"Short":[43],"Answer":[44],"Grading":[45],"(SAG)":[46],"systems":[47],"aim":[48],"automatically":[50],"score":[51],"students'":[52],"answers":[53],"in":[54,58,90,120],"examinations.":[55],"Despite":[56],"growth":[57],"SAG":[59,136,164],"methods":[60,89],"capabilities,":[62],"exists":[64],"no":[65],"comprehensive":[66],"short-answer":[67,117],"benchmark":[69,104],"across":[70],"different":[71],"subjects,":[72],"scales,":[74],"distributions.":[76],"Thus,":[77],"it":[78],"is":[79],"hard":[80],"assess":[82],"capabilities":[84],"of":[85,92,109,134],"current":[86],"automated":[87,110],"terms":[91],"their":[93],"generalizability.":[94],"In":[95],"this":[96],"preliminary":[97],"work,":[98],"we":[99,130],"introduce":[100],"combined":[102],"ASAG2024":[103],"facilitate":[106],"comparison":[108],"systems.":[112,165],"Combining":[113],"seven":[114],"commonly":[115],"used":[116],"datasets":[119],"common":[122],"structure":[123],"scale.":[126],"For":[127],"our":[128],"benchmark,":[129],"evaluate":[131],"set":[133],"recent":[135],"methods,":[137],"revealing":[138],"that":[139],"while":[140],"LLM-based":[141],"approaches":[142],"reach":[143],"new":[144],"high":[145],"scores,":[146],"they":[147],"still":[148],"far":[150],"from":[151],"reaching":[152],"human":[153],"performance.":[154],"This":[155],"opens":[156],"avenues":[158],"for":[159],"future":[160],"research":[161],"on":[162],"human-machine":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}