{"id":"https://openalex.org/W7141148890","doi":"https://doi.org/10.48550/arxiv.2603.25133","title":"RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following","display_name":"RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141148890","doi":"https://doi.org/10.48550/arxiv.2603.25133"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25133","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25133","pdf_url":null,"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":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.2603.25133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081439632","display_name":"Tianjun Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Tianjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027410770","display_name":"Xuan Lin","orcid":"https://orcid.org/0000-0001-7216-1821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130789258","display_name":"Wenyan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Wenyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130787152","display_name":"Qianyu He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Qianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130782399","display_name":"Shisong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shisong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004450665","display_name":"Li-Cai Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Licai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130779676","display_name":"Wanqing Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wanqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130755718","display_name":"Hongwei Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Hongwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130811282","display_name":"Bo Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130744838","display_name":"Yanghua Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Yanghua","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/T10028","display_name":"Topic Modeling","score":0.24650000035762787,"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/T10028","display_name":"Topic Modeling","score":0.24650000035762787,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09120000153779984,"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":0.08810000121593475,"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/rubric","display_name":"Rubric","score":0.8920000195503235},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8034999966621399},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6158000230789185},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.555400013923645},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4961000084877014},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3560999929904938}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.8920000195503235},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8034999966621399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7434999942779541},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.555400013923645},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4650999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4499000012874603},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25133","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25133","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.25133","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25133","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rubric-based":[0],"evaluation":[1,50,127,130],"has":[2],"become":[3],"a":[4,85,113],"prevailing":[5],"paradigm":[6],"for":[7,29,69,158],"evaluating":[8],"instruction":[9,70],"following":[10],"in":[11,117],"large":[12],"language":[13],"models":[14],"(LLMs).":[15],"Despite":[16],"its":[17],"widespread":[18],"use,":[19],"the":[20,38,44,64],"reliability":[21],"of":[22,88],"these":[23],"rubric-level":[24,66,105,129],"evaluations":[25],"remains":[26,107],"unclear,":[27],"calling":[28],"meta-evaluation.":[30],"However,":[31],"prior":[32],"meta-evaluation":[33,67],"efforts":[34],"largely":[35],"focus":[36],"on":[37,123],"response":[39],"level,":[40],"failing":[41],"to":[42],"assess":[43],"fine-grained":[45],"judgment":[46],"accuracy":[47],"that":[48,96,104],"rubric-based":[49],"relies":[51],"on.":[52],"To":[53],"bridge":[54],"this":[55],"gap,":[56],"we":[57,148],"introduce":[58],"RubricEval.":[59],"Our":[60,101],"benchmark":[61,68],"features:":[62],"(1)":[63],"first":[65],"following,":[71],"(2)":[72],"diverse":[73],"instructions":[74],"and":[75,80,83,137,154],"responses":[76],"spanning":[77],"multiple":[78],"categories":[79],"model":[81],"sources,":[82],"(3)":[84],"substantial":[86],"set":[87],"3,486":[89],"quality-controlled":[90],"instances,":[91],"along":[92],"with":[93],"Easy/Hard":[94],"subsets":[95],"better":[97],"differentiates":[98],"judge":[99,116],"performance.":[100],"experiments":[102],"reveal":[103],"judging":[106],"far":[108],"from":[109],"solved:":[110],"even":[111],"GPT-4o,":[112],"widely":[114],"adopted":[115],"instruction-following":[118,160],"benchmarks,":[119],"achieves":[120],"only":[121],"55.97%":[122],"Hard":[124],"subset.":[125],"Considering":[126],"paradigm,":[128],"outperforms":[131],"checklist-level,":[132],"explicit":[133],"reasoning":[134],"improves":[135],"accuracy,":[136],"both":[138],"together":[139],"reduce":[140],"inter-judge":[141],"variance.":[142],"Through":[143],"our":[144],"established":[145],"rubric":[146],"taxonomy,":[147],"further":[149],"identify":[150],"common":[151],"failure":[152],"modes":[153],"offer":[155],"actionable":[156],"insights":[157],"reliable":[159],"evaluation.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-28T00:00:00"}