{"id":"https://openalex.org/W7127623344","doi":"https://doi.org/10.1145/3769002.3769962","title":"Grade Like a Human: Rethinking Automated Assessment with Large Language Models","display_name":"Grade Like a Human: Rethinking Automated Assessment with Large Language Models","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7127623344","doi":"https://doi.org/10.1145/3769002.3769962"},"language":null,"primary_location":{"id":"doi:10.1145/3769002.3769962","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769002.3769962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","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/A5100678493","display_name":"Wenjing Xie","orcid":"https://orcid.org/0000-0002-0857-4426"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wenjing Xie","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113414011","display_name":"Juxin Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Juxin Niu","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chun Jason Xue","orcid":"https://orcid.org/0000-0002-6431-9868"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Chun Jason Xue","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125035356","display_name":"Nan Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nan Guan","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100678493"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":2.4849,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93682153,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.3714999854564667,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.3714999854564667,"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/T10959","display_name":"Student Assessment and Feedback","score":0.11990000307559967,"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/T11122","display_name":"Online Learning and Analytics","score":0.09099999815225601,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rubric","display_name":"Rubric","score":0.9617000222206116},{"id":"https://openalex.org/keywords/grading","display_name":"Grading (engineering)","score":0.8501999974250793},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6718000173568726},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41760000586509705},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4156000018119812},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.9617000222206116},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.8501999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738099992275238},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6718000173568726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4417000114917755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4406999945640564},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3571000099182129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C73126755","wikidata":"https://www.wikidata.org/wiki/Q7598408","display_name":"Standards-based assessment","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C2777898490","wikidata":"https://www.wikidata.org/wiki/Q17157236","display_name":"Writing assessment","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769002.3769962","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3769002.3769962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W4377095850","https://openalex.org/W4391573863","https://openalex.org/W4393119218","https://openalex.org/W4393145752","https://openalex.org/W4396680517","https://openalex.org/W4401042688","https://openalex.org/W4411630288"],"related_works":[],"abstract_inverted_index":{"Grading":[0],"is":[1],"a":[2,16,88,112,130],"foundational":[3],"component":[4],"of":[5],"assessment":[6],"in":[7,15,45,68,72,82,129,162],"higher":[8],"education,":[9],"aiming":[10],"to":[11,106],"evaluate":[12,117],"student":[13,140,149],"work":[14,52],"reliable,":[17],"repeatable,":[18],"and":[19,28,41,48,71,76,110,126,139,151,165],"interpretable":[20],"manner.":[21],"Short-answer":[22],"questions":[23,138],"effectively":[24],"assess":[25],"understanding,":[26],"analysis,":[27],"articulation,":[29],"but":[30],"their":[31],"open-ended":[32],"nature":[33],"makes":[34],"traditional":[35],"workflows":[36],"reliant":[37],"on":[38,120],"detailed":[39],"rubrics":[40,99],"manual":[42],"review,":[43],"resulting":[44],"substantial":[46,160],"time":[47],"labor.":[49],"Although":[50],"recent":[51],"has":[53],"explored":[54],"using":[55,136],"large":[56],"language":[57],"models":[58],"(LLMs)":[59],"for":[60,142],"automated":[61],"short-answer":[62,123],"grading":[63,124,152],"(ASAG),":[64],"significant":[65],"gaps":[66],"remain":[67],"rubric":[69],"design":[70],"ensuring":[73],"scoring":[74,108],"consistency":[75],"fairness.":[77,166],"Inspired":[78],"by":[79],"best":[80],"practices":[81],"human":[83],"grading,":[84],"we":[85],"propose":[86],"Grade-Like-a-Human,":[87],"systematic":[89],"multi-agent":[90],"framework":[91],"that":[92],"spans":[93],"the":[94,147,155],"full":[95],"pipeline:":[96],"iteratively":[97],"aligning":[98],"with":[100],"real":[101,131],"answers,":[102],"leveraging":[103],"cross-item":[104],"memory":[105],"enhance":[107],"consistency,":[109,164],"integrating":[111],"post-grading":[113],"audit-and-feedback":[114],"loop.":[115],"We":[116,144],"our":[118],"method":[119],"an":[121],"open-source":[122],"benchmark":[125],"deploy":[127],"it":[128],"undergraduate":[132],"Operating":[133],"Systems":[134],"course,":[135],"authentic":[137],"submissions":[141],"evaluation.":[143],"further":[145],"release":[146],"questions,":[148],"submissions,":[150],"artifacts":[153],"as":[154],"OS":[156],"dataset1.":[157],"Experiments":[158],"demonstrate":[159],"improvements":[161],"accuracy,":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-06T00:00:00"}
