{"id":"https://openalex.org/W7159661928","doi":"https://doi.org/10.1145/3808045.3808093","title":"MultEval: Supporting Collaborative Alignment for LLM-as-a-Judge Evaluation Criteria","display_name":"MultEval: Supporting Collaborative Alignment for LLM-as-a-Judge Evaluation Criteria","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7159661928","doi":"https://doi.org/10.1145/3808045.3808093"},"language":null,"primary_location":{"id":"doi:10.1145/3808045.3808093","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808045.3808093","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Annual Symposium on Human-Computer Interaction for Work","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3808045.3808093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109909965","display_name":"Charles Chiang","orcid":"https://orcid.org/0009-0008-6079-4355"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Chiang","raw_affiliation_strings":["University of Notre Dame, Notre Dame, Indiana, USA"],"raw_orcid":"https://orcid.org/0009-0008-6079-4355","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134947549","display_name":"Simret Gebreegziabher","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simret Gebreegziabher","raw_affiliation_strings":["University of Notre Dame, Notre Dame, Indiana, USA"],"raw_orcid":"https://orcid.org/0000-0002-1772-6065","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093206754","display_name":"Annalisa Szymanski","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Annalisa Szymanski","raw_affiliation_strings":["University of Notre Dame, Notre Dame, Indiana, USA"],"raw_orcid":"https://orcid.org/0009-0009-5472-282X","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102965060","display_name":"Yukun Yang","orcid":"https://orcid.org/0009-0003-1971-4468"},"institutions":[{"id":"https://openalex.org/I4210087032","display_name":"Cambridge Scientific (United States)","ror":"https://ror.org/001s4dh65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyo Jin Do","raw_affiliation_strings":["IBM Research, Cambridge, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0001-8297-6792","affiliations":[{"raw_affiliation_string":"IBM Research, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210087032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134961667","display_name":"Hyo Jin Do","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zahra Ashktorab","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-0686-7911","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003440919","display_name":"Zahra Ashktorab","orcid":"https://orcid.org/0000-0002-0686-7911"},"institutions":[{"id":"https://openalex.org/I4210087032","display_name":"Cambridge Scientific (United States)","ror":"https://ror.org/001s4dh65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Werner Geyer","raw_affiliation_strings":["IBM Research, Cambridge, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0003-4699-5026","affiliations":[{"raw_affiliation_string":"IBM Research, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210087032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022799238","display_name":"Werner Geyer","orcid":"https://orcid.org/0000-0003-4699-5026"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toby Jia-Jun Li","raw_affiliation_strings":["University of Notre Dame, Notre Dame, Indiana, USA"],"raw_orcid":"https://orcid.org/0000-0001-7902-7625","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134906589","display_name":"Toby Li","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Gomez-Zara","raw_affiliation_strings":["University of Notre Dame, Notre Dame, Indiana, USA"],"raw_orcid":"https://orcid.org/0000-0002-4609-6293","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61992446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.4952999949455261,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.4952999949455261,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.06069999933242798,"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"}},{"id":"https://openalex.org/T13851","display_name":"Law, AI, and Intellectual Property","score":0.04690000042319298,"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/formative-assessment","display_name":"Formative assessment","score":0.67330002784729},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.6653000116348267},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5209000110626221},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47850000858306885},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4133000075817108},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C42525527","wikidata":"https://www.wikidata.org/wiki/Q1209955","display_name":"Formative assessment","level":2,"score":0.67330002784729},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.6653000116348267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643999814987183},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.47850000858306885},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.36000001430511475},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C152747807","wikidata":"https://www.wikidata.org/wiki/Q1854913","display_name":"Summative assessment","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C559553711","wikidata":"https://www.wikidata.org/wiki/Q1145523","display_name":"Collaboration","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C554579003","wikidata":"https://www.wikidata.org/wiki/Q474157","display_name":"Collaborative software","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3808045.3808093","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808045.3808093","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Annual Symposium on Human-Computer Interaction for Work","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.26679","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.26679","pdf_url":"https://arxiv.org/pdf/2604.26679","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3808045.3808093","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808045.3808093","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Annual Symposium on Human-Computer Interaction for Work","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1715413448","display_name":"Collaborative Research: SaTC: CORE: Small: Empathy-Based Privacy Education and Design through Synthetic Persona Data Generation","funder_award_id":"2426395","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4799765378","display_name":null,"funder_award_id":"CNS-2426395","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7829645069","display_name":null,"funder_award_id":"2025 Ph.D. Fellowship","funder_id":"https://openalex.org/F4320307762","funder_display_name":"International Business Machines Corporation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM-as-a-judge":[0,80],"approaches":[1],"have":[2],"emerged":[3],"as":[4],"a":[5,21,38,66,126,168,173],"scalable":[6],"solution":[7],"for":[8,79,116],"evaluating":[9],"model":[10],"behaviors,":[11],"yet":[12],"they":[13],"rely":[14],"on":[15,120],"evaluation":[16,77],"criteria":[17,36,78,110,131,146,191],"often":[18],"created":[19],"by":[20,55,132],"single":[22],"individual,":[23],"embedding":[24],"that":[25,111,128],"person\u2019s":[26],"assumptions,":[27],"priorities,":[28,103],"and":[29,40,50,75,102,104,114,138,150,153,187],"interpretive":[30],"lens.":[31],"In":[32],"practice,":[33],"defining":[34],"such":[35],"is":[37],"collaborative":[39,130,188],"contested":[41],"process":[42],"involving":[43],"multiple":[44,134],"stakeholders":[45,71,98],"with":[46,99,147],"different":[47,100],"values,":[48],"interpretations,":[49],"priorities\u2014an":[51],"aspect":[52],"largely":[53],"unsupported":[54],"existing":[56],"tools.":[57],"To":[58],"examine":[59],"this":[60],"problem":[61],"in":[62,86,91,171],"depth,":[63],"we":[64,123],"present":[65],"formative":[67],"study":[68,170],"examining":[69],"how":[70,157,185],"collaboratively":[72,181],"create,":[73],"negotiate,":[74],"refine":[76],"systems.":[81],"Our":[82],"findings":[83],"reveal":[84],"challenges":[85],"human":[87,107],"oversight,":[88],"including":[89],"difficulties":[90],"establishing":[92],"shared":[93],"understanding,":[94],"aligning":[95],"values":[96],"across":[97],"expertise":[101],"translating":[105],"nuanced":[106],"judgments":[108,158],"into":[109,161],"are":[112,159],"interpretable":[113],"actionable":[115],"LLM":[117],"judges.":[118],"Based":[119],"these":[121],"insights,":[122],"developed":[124],"MultEval,":[125],"system":[127],"supports":[129],"enabling":[133],"evaluators":[135],"to":[136,180],"surface":[137],"diagnose":[139],"disagreements":[140],"using":[141],"consensus-building":[142],"theory,":[143],"iteratively":[144],"revise":[145],"attached":[148],"examples":[149],"proposal":[151],"history,":[152],"maintain":[154],"transparency":[155],"over":[156],"encoded":[160],"an":[162],"automated":[163],"evaluator.":[164],"We":[165],"further":[166],"report":[167],"case":[169],"which":[172],"team":[174],"of":[175],"domain":[176],"experts":[177],"used":[178],"MultEval":[179],"author":[182],"criteria,":[183],"illustrating":[184],"coordination":[186],"consensus-making":[189],"shape":[190],"evolution.":[192]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-05-02T00:00:00"}