{"id":"https://openalex.org/W4410356725","doi":"https://doi.org/10.1145/3672608.3707736","title":"Assessing the Real-World Impact of Disagreement Between Human Graders and LLMs","display_name":"Assessing the Real-World Impact of Disagreement Between Human Graders and LLMs","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410356725","doi":"https://doi.org/10.1145/3672608.3707736"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115904919","display_name":"Sebastian Speiser","orcid":"https://orcid.org/0009-0007-6587-1527"},"institutions":[{"id":"https://openalex.org/I31582689","display_name":"Stuttgart University of Applied Sciences","ror":"https://ror.org/039gdg280","country_code":"DE","type":"education","lineage":["https://openalex.org/I31582689"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sebastian Speiser","raw_affiliation_strings":["Hochschule f\u00fcr Technik, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Hochschule f\u00fcr Technik, Stuttgart, Germany","institution_ids":["https://openalex.org/I31582689"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5115904919"],"corresponding_institution_ids":["https://openalex.org/I31582689"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05232283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9854000210762024,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9854000210762024,"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/T11122","display_name":"Online Learning and Analytics","score":0.9848999977111816,"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/T10028","display_name":"Topic Modeling","score":0.9713000059127808,"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":0.43192464113235474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43192464113235474}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672608.3707736","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672608.3707736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1967082761","https://openalex.org/W3170923959","https://openalex.org/W4295714264","https://openalex.org/W4323338676","https://openalex.org/W4396681086"],"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":{"Applying":[0],"artificial":[1],"intelligence":[2],"models":[3],"to":[4,81,108,170],"grade":[5],"student":[6,112],"answers":[7,80],"is":[8,29,152],"a":[9,90,171,176],"popular":[10],"application.":[11],"Lately":[12],"Large":[13],"Language":[14],"Models":[15],"(LLMs)":[16],"have":[17],"shown":[18],"promising":[19],"results.":[20],"However,":[21],"the":[22,42,59,97,100,114,125,128,131,143,147,150],"disagreement":[23,47,151],"between":[24],"human":[25,121,138,178],"graders":[26],"and":[27,124,167],"LLMs":[28],"often":[30],"considered":[31],"too":[32],"large":[33],"for":[34,77,154],"practical":[35],"adoption.":[36],"In":[37],"this":[38,46,165],"paper,":[39],"we":[40,57],"investigate":[41],"real-world":[43,101],"impact":[44,102,148],"of":[45,52,62,99,110,116,127,133,149],"on":[48,54,103],"final":[49,155],"grades.":[50],"Instead":[51],"focusing":[53],"individual":[55,79,111,161],"answers,":[56,113],"simulate":[58],"grading":[60,78,117,122,172],"process":[61],"an":[63,68],"entire":[64],"exam.":[65],"We":[66,163],"use":[67],"unmodified":[69],"LLM":[70],"(OpenAI":[71],"GPT-3.5":[72],"Turbo)":[73],"with":[74],"one-shot":[75],"prompting":[76],"short":[82],"answer":[83],"questions":[84],"from":[85],"computer":[86],"science":[87],"courses":[88],"at":[89,160],"German":[91],"university.":[92],"Our":[93],"main":[94],"contributions":[95],"are":[96],"evaluation":[98],"examination":[104],"grades":[105,156],"in":[106,120,130],"contrast":[107],"correctness":[109],"simulation":[115],"strategies":[118],"common":[119],"practice,":[123],"discussion":[126],"results":[129],"context":[132],"observed":[134],"inter-rater":[135],"variabilities":[136],"among":[137],"graders.":[139],"The":[140],"findings":[141],"confirm":[142],"natural":[144],"expectation":[145],"that":[146],"lower":[153],"than":[157],"when":[158],"looking":[159],"answers.":[162],"quantify":[164],"effect":[166],"compare":[168],"it":[169],"obtained":[173],"by":[174],"simulating":[175],"second":[177],"grader.":[179]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}