{"id":"https://openalex.org/W7165047943","doi":"https://doi.org/10.48550/arxiv.2606.17507","title":"LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline","display_name":"LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7165047943","doi":"https://doi.org/10.48550/arxiv.2606.17507"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17507","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.17507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138811360","display_name":"Xiwei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138788710","display_name":"Chen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069083047","display_name":"Jacky Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jacky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075044856","display_name":"Phil Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Phil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138793770","display_name":"Qian Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092636599","display_name":"Mohan Dhall","orcid":"https://orcid.org/0000-0002-3809-2663"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhall, Mohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138764800","display_name":"Wenjie Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005096654","display_name":"Lei Zhu","orcid":"https://orcid.org/0009-0003-3762-8344"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Liming","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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.3479999899864197,"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":0.3479999899864197,"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/T10028","display_name":"Topic Modeling","score":0.13420000672340393,"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":0.03709999844431877,"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/pipeline","display_name":"Pipeline (software)","score":0.7584999799728394},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7261999845504761},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6022999882698059},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.59170001745224},{"id":"https://openalex.org/keywords/glossary","display_name":"Glossary","score":0.570900022983551},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5666999816894531},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4138999879360199}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7584999799728394},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7261999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6057999730110168},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C2780031656","wikidata":"https://www.wikidata.org/wiki/Q859161","display_name":"Glossary","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C110354214","wikidata":"https://www.wikidata.org/wiki/Q6314146","display_name":"Engineering management","level":1,"score":0.37929999828338623},{"id":"https://openalex.org/C45504901","wikidata":"https://www.wikidata.org/wiki/Q935222","display_name":"Syllabus","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C42525527","wikidata":"https://www.wikidata.org/wiki/Q1209955","display_name":"Formative assessment","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3172999918460846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C2779891390","wikidata":"https://www.wikidata.org/wiki/Q964630","display_name":"Custodians","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C2779011557","wikidata":"https://www.wikidata.org/wiki/Q16911265","display_name":"Curriculum development","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17507","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2606.17507","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.8340198993682861,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"AI":[1],"and":[2,13,42,79,85,88,106,113,132,135,151,183,207],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"are":[7,176],"increasingly":[8],"applied":[9],"to":[10,65,91,122,140,143,169,179],"question":[11],"generation":[12],"automated":[14],"assessment.":[15],"However,":[16],"deploying":[17],"LLMs":[18],"in":[19,38],"preparation":[20,68],"for":[21,57,69],"high-stakes":[22],"exams":[23],"requires":[24],"more":[25,177],"than":[26],"prompt":[27],"engineering;":[28],"it":[29],"demands":[30],"software":[31],"pipelines":[32],"that":[33,160,175],"systematically":[34],"ground":[35],"model":[36],"outputs":[37],"authorised":[39,89,180],"curriculum":[40,181],"artefacts":[41,182],"marking":[43,137,155,166,184],"guidelines":[44],"issued":[45],"by":[46],"education":[47],"authorities.":[48],"This":[49,146],"paper":[50],"presents":[51],"a":[52,83],"curriculum-grounded,":[53],"configurable":[54],"LLM-as-Judge":[55,163],"pipeline":[56,73,164,187],"question-level":[58],"marking,":[59],"co-developed":[60],"with":[61,153],"an":[62,193],"industrial":[63],"partner,":[64],"support":[66,92],"exam":[67],"university":[70],"admission.":[71],"The":[72,186],"identifies":[74],"the":[75,161],"relevant":[76],"topics,":[77],"subtopics,":[78],"cognitive":[80],"demand":[81],"of":[82,130],"question,":[84],"assembles":[86],"verifiable":[87],"context":[90],"LLM":[93,118],"judgement.":[94],"Curriculum":[95],"intent":[96],"is":[97,120],"operationalised":[98],"through":[99],"concrete":[100],"syllabus":[101],"artefacts,":[102],"including":[103],"prescribed":[104],"verbs":[105],"outcomes,":[107],"performance":[108],"band":[109],"descriptors,":[110],"glossary":[111],"definitions,":[112],"marking-guideline":[114],"principles.":[115],"A":[116],"staged":[117],"workflow":[119],"employed":[121],"first":[123],"generate":[124],"question-specific":[125],"rubrics,":[126],"capturing":[127],"structured":[128],"expectations":[129],"performance,":[131],"then":[133],"derive":[134],"evaluate":[136],"criteria":[138],"used":[139],"allocate":[141],"marks":[142],"student":[144],"responses.":[145],"design":[147],"improves":[148],"consistency,":[149],"transparency,":[150],"alignment":[152],"official":[154],"practices.":[156],"Preliminary":[157],"evaluation":[158],"shows":[159],"proposed":[162],"delivers":[165],"outcomes":[167],"comparable":[168],"human":[170],"tutors,":[171],"while":[172],"yielding":[173],"justifications":[174],"traceable":[178],"standards.":[185],"has":[188],"also":[189],"been":[190],"integrated":[191],"into":[192,204],"online":[194],"study":[195],"platform,":[196],"where":[197],"early":[198],"deployment":[199],"data":[200],"provide":[201],"initial":[202],"insights":[203],"operational":[205],"usage":[206],"manual":[208],"overrides.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-18T00:00:00"}
