{"id":"https://openalex.org/W7164002160","doi":"https://doi.org/10.48550/arxiv.2606.08625","title":"From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape","display_name":"From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape","publication_year":2026,"publication_date":"2026-06-07","ids":{"openalex":"https://openalex.org/W7164002160","doi":"https://doi.org/10.48550/arxiv.2606.08625"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08625","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08625","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.2606.08625","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138246492","display_name":"Hao Chen (5190)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138212243","display_name":"Ziyu Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Ziyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138247555","display_name":"Yukun Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yukun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138239595","display_name":"Qingfu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Qingfu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138235544","display_name":"Maosong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Maosong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138220424","display_name":"Wanxiang Che","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che, Wanxiang","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2207999974489212,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2207999974489212,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.1468999981880188,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.1256999969482422,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rubric","display_name":"Rubric","score":0.9860000014305115},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4212000072002411},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.3792000114917755},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.35440000891685486}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.9860000014305115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6158000230789185},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.35440000891685486},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C53839665","wikidata":"https://www.wikidata.org/wiki/Q2067088","display_name":"Peer assessment","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26919999718666077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08625","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08625","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.2606.08625","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08625","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":[{"score":0.4678225815296173,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"advance":[5],"toward":[6],"open-ended":[7],"autonomous":[8],"agents,":[9],"the":[10,25,114,125,143,192],"mechanisms":[11],"used":[12],"to":[13,40],"evaluate":[14],"and":[15,55,72,75,96,98,104,166,180,198],"guide":[16],"their":[17,78,94,100],"behavior":[18],"must":[19],"evolve":[20],"accordingly.":[21],"This":[22],"work":[23],"introduces":[24],"rubric":[26,91,157],"as":[27,36,61,130,191],"a":[28,37],"unifying":[29],"framework":[30],"capturing":[31],"this":[32],"evolution,":[33],"characterizing":[34],"rubrics":[35,60,182],"dynamic":[38],"response":[39],"successive":[41],"LLM":[42],"paradigm":[43],"shifts":[44],"that":[45,65,77],"recurs":[46],"across":[47,80,102,159,173],"otherwise":[48],"independent":[49],"efforts":[50],"in":[51],"evaluation,":[52],"reinforcement":[53],"learning,":[54],"safety":[56],"alignment.":[57],"We":[58,87,154],"define":[59],"explicit":[62],"criteria":[63],"sets":[64],"transform":[66],"complex":[67],"quality":[68],"judgments":[69,120],"into":[70,121,187],"structured":[71],"actionable":[73],"standards,":[74],"demonstrate":[76],"recurrence":[79],"these":[81],"research":[82],"threads":[83],"is":[84],"not":[85],"coincidental.":[86],"systematically":[88],"organize":[89],"existing":[90],"designs,":[92],"examine":[93],"construction":[95],"optimization,":[97],"analyze":[99],"role":[101],"evaluation":[103],"training.":[105],"Rubrics":[106],"manifest":[107],"at":[108,113,124,142],"three":[109],"progressively":[110],"deeper":[111],"levels:":[112],"evaluative":[115],"level,":[116,127,145],"they":[117,128,146],"decompose":[118],"holistic":[119],"verifiable":[122],"dimensions;":[123],"training":[126],"serve":[129],"dense":[131],"feedback":[132],"signals":[133],"providing":[134],"process-level":[135],"guidance":[136],"where":[137],"scalar":[138],"rewards":[139],"fall":[140],"short;":[141],"intrinsic":[144],"emerge":[147],"dynamically":[148],"from":[149],"model":[150],"behaviors,":[151],"driving":[152],"self-improvement.":[153],"further":[155],"assess":[156],"reliability":[158],"generation":[160],"quality,":[161],"execution":[162],"fidelity,":[163],"theoretical":[164],"constraints,":[165],"security":[167],"threats,":[168],"before":[169],"surveying":[170],"rubric-based":[171],"benchmarks":[172],"diverse":[174],"domains.":[175],"By":[176],"rendering":[177],"assessment":[178],"transparent":[179],"decomposable,":[181],"translate":[183],"human":[184,196],"value":[185],"expectations":[186],"machine-learnable":[188],"signals,":[189],"serving":[190],"enduring":[193],"bridge":[194],"between":[195],"intentions":[197],"machine":[199],"behavior.":[200]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}