{"id":"https://openalex.org/W7214909558","doi":"https://doi.org/10.48550/arxiv.2609.37322","title":"Mubric: Mutation Testing-Guided Rubric Generation for LLM Evaluation","display_name":"Mubric: Mutation Testing-Guided Rubric Generation for LLM Evaluation","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214909558","doi":"https://doi.org/10.48550/arxiv.2609.37322"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37322","pdf_url":"https://arxiv.org/pdf/2609.37322","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37322","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144290363","display_name":"Jiayuxuan Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Jiayuxuan","raw_affiliation_strings":["Tsinghua University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University ,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088708850","display_name":"Jie M. Zhang","orcid":"https://orcid.org/0000-0003-0481-7264","observed_orcids":["https://orcid.org/0000-0003-0481-7264","https://orcid.org/0000-0001-7733-5392"]},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhang, Jie M.","raw_affiliation_strings":["King's College London ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London ,","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153645722","display_name":"Yiling Lou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lou, Yiling","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031457464","display_name":"Zhenpeng Chen","orcid":"https://orcid.org/0000-0002-4765-1893","observed_orcids":["https://orcid.org/0000-0002-4765-1893"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhenpeng","raw_affiliation_strings":["Tsinghua University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University ,","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.6815999746322632,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.6815999746322632,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.10159999877214432,"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":0.06430000066757202,"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-generation","display_name":"rubric generation","score":0.9700000286102295},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.7950000166893005},{"id":"https://openalex.org/keywords/mutation-testing","display_name":"mutation testing","score":0.9879999756813049},{"id":"https://openalex.org/keywords/mutation-operator","display_name":"mutation operator","score":0.6740000247955322},{"id":"https://openalex.org/keywords/response-quality","display_name":"response quality","score":0.6549999713897705},{"id":"https://openalex.org/keywords/grading-criteria","display_name":"grading criteria","score":0.6790000200271606},{"id":"https://openalex.org/keywords/automated-assessment","display_name":"automated assessment","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.9639000296592712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.590399980545044},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.5145000219345093},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.4997999966144562},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4578000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C163565370","wikidata":"https://www.wikidata.org/wiki/Q4308623","display_name":"Mutation testing","level":4,"score":0.3619999885559082},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.30320000648498535},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37322","pdf_url":"https://arxiv.org/pdf/2609.37322","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37322","doi":"https://doi.org/10.48550/arxiv.2609.37322","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37322","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37322","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37322","pdf_url":"https://arxiv.org/pdf/2609.37322","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214909558.pdf","grobid_xml":"https://content.openalex.org/works/W7214909558.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4403884725","https://openalex.org/W6891853064","https://openalex.org/W7163068252","https://openalex.org/W7167225266"],"related_works":["https://openalex.org/W7169497493","https://openalex.org/W7140346651","https://openalex.org/W7204954649","https://openalex.org/W7202185450","https://openalex.org/W7163068252","https://openalex.org/W7221153465","https://openalex.org/W7204157769","https://openalex.org/W7164002160","https://openalex.org/W7208783751","https://openalex.org/W7163013473"],"abstract_inverted_index":{"Rubric-based":[0],"evaluation":[1,174],"is":[2],"widely":[3],"used":[4],"to":[5,36,116,132,149],"assess":[6],"LLM-based":[7],"systems":[8],"by":[9,50,180],"decomposing":[10],"response":[11,87,122,142],"quality":[12,25,77],"into":[13,53,83,109],"task-specific":[14,24],"scoring":[15],"criteria.":[16],"However,":[17],"automatically":[18],"generating":[19],"rubrics":[20],"that":[21],"reliably":[22],"capture":[23],"requirements":[26],"remains":[27],"challenging.":[28],"We":[29,62,153],"introduce":[30,117],"Mubric,":[31],"a":[32,41,47,72,80,118,125,133],"mutation":[33,111],"testing-guided":[34],"approach":[35],"rubric":[37,73,166],"generation.":[38],"Mutation":[39],"testing,":[40],"classic":[42],"software":[43],"testing":[44],"methodology,":[45],"evaluates":[46],"test":[48,67],"suite":[49],"injecting":[51],"faults":[52],"programs":[54],"and":[55,69,102,105,144],"checking":[56],"whether":[57,137],"the":[58,138,151,171,177],"tests":[59],"detect":[60],"them.":[61],"draw":[63],"an":[64,75,84],"analogy":[65],"between":[66],"suites":[68],"rubrics:":[70],"if":[71],"captures":[74],"important":[76],"requirement,":[78],"introducing":[79],"corresponding":[81],"defect":[82],"otherwise":[85],"high-quality":[86],"should":[88],"reduce":[89,141],"its":[90],"score.":[91],"Mubric":[92,155,169],"first":[93],"mines":[94],"common":[95],"defects":[96,108,140,148],"from":[97],"real":[98],"pairs":[99],"of":[100,121],"preferred":[101],"dispreferred":[103],"responses":[104],"abstracts":[106],"these":[107],"reusable":[110],"operators,":[112],"each":[113],"specifying":[114],"how":[115],"particular":[119],"type":[120],"defect.":[123],"For":[124],"new":[126],"task,":[127],"it":[128],"applies":[129],"relevant":[130],"operators":[131],"reference":[134],"response,":[135],"checks":[136],"injected":[139],"quality,":[143],"uses":[145],"insufficiently":[146],"penalized":[147],"refine":[150],"rubric.":[152],"evaluate":[154],"on":[156],"703":[157],"tasks":[158],"across":[159],"four":[160],"representative":[161],"domains":[162],"against":[163],"six":[164],"advanced":[165],"generation":[167],"methods.":[168],"achieves":[170],"highest":[172],"overall":[173],"accuracy,":[175],"outperforming":[176],"strongest":[178],"baseline":[179],"7.48":[181],"percentage":[182],"points.":[183]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-01T00:00:00"}