{"id":"https://openalex.org/W7224437250","doi":"https://doi.org/10.18653/2026.findings-emnlp.1108","title":"CompassJudger-2: A Holistic Approach Towards Generalist Judge Model","display_name":"CompassJudger-2: A Holistic Approach Towards Generalist Judge Model","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224437250","doi":"https://doi.org/10.18653/2026.findings-emnlp.1108"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1108","doi":"https://doi.org/10.18653/2026.findings-emnlp.1108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1108","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1108.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.1108.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160072467","display_name":"Taolin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"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":"Taolin Zhang","raw_affiliation_strings":["Shanghai AI Laboratory","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160107231","display_name":"Zihan Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Ma","raw_affiliation_strings":["Shanghai AI Laboratory","Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160090415","display_name":"Maosongcao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maosongcao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160126342","display_name":"Shudong Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","MO"],"is_corresponding":false,"raw_author_name":"Shudong Liu","raw_affiliation_strings":["Shanghai AI Laboratory","University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010328805","display_name":"Junnan Liu","orcid":"https://orcid.org/0009-0007-7801-9720","observed_orcids":["https://orcid.org/0009-0007-7801-9720"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junnan Liu","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747790","display_name":"Songyang Zhang","orcid":"https://orcid.org/0000-0002-0008-609X","observed_orcids":["https://orcid.org/0000-0002-0008-609X"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songyang Zhang","raw_affiliation_strings":["Tencent Hunyuan GitHub"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Hunyuan GitHub","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437924","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6384-0355","observed_orcids":["https://orcid.org/0000-0001-6384-0355"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.76106234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23442","last_page":"23461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8057000041007996,"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":0.8057000041007996,"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":0.12250000238418579,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0142000000923872,"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/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.902999997138977},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.8960000276565552},{"id":"https://openalex.org/keywords/subjective-evaluation","display_name":"subjective evaluation","score":0.9980000257492065},{"id":"https://openalex.org/keywords/rejection-sampling","display_name":"rejection sampling","score":0.7409999966621399},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.7720000147819519},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.5680000185966492}],"concepts":[{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.47029998898506165},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36239999532699585},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3490000069141388},{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C95124753","wikidata":"https://www.wikidata.org/wiki/Q875686","display_name":"Environmental ethics","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2770000100135803},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1108","doi":"https://doi.org/10.18653/2026.findings-emnlp.1108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1108","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1108.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.1108","doi":"https://doi.org/10.18653/2026.findings-emnlp.1108","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1108","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1108.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224437250.pdf","grobid_xml":"https://content.openalex.org/works/W7224437250.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W3193589100","https://openalex.org/W3210904070","https://openalex.org/W4387560040","https://openalex.org/W4387994739","https://openalex.org/W4388718089","https://openalex.org/W4392822190","https://openalex.org/W4393063868","https://openalex.org/W4394708144","https://openalex.org/W4399836654","https://openalex.org/W4401306886","https://openalex.org/W4402684121","https://openalex.org/W4403583114","https://openalex.org/W4404089439","https://openalex.org/W4404783058","https://openalex.org/W4405655184","https://openalex.org/W4405903187","https://openalex.org/W4412944762","https://openalex.org/W4414281281","https://openalex.org/W4414490998","https://openalex.org/W4414786516","https://openalex.org/W4414886170","https://openalex.org/W4414939355","https://openalex.org/W4415161187","https://openalex.org/W4416036315","https://openalex.org/W4416123545","https://openalex.org/W4417299315","https://openalex.org/W7166887355"],"related_works":["https://openalex.org/W7224387187","https://openalex.org/W6891849393","https://openalex.org/W7224260181","https://openalex.org/W4412886639","https://openalex.org/W7166852156","https://openalex.org/W6903827461","https://openalex.org/W7224499908","https://openalex.org/W4416037109","https://openalex.org/W7196936216","https://openalex.org/W7166796117"],"abstract_inverted_index":{"Recently,":[0],"the":[1,44,98],"role":[2],"of":[3,46,88],"LLM-as-judge":[4],"in":[5],"evaluating":[6],"large":[7],"language":[8],"models":[9,26],"has":[10],"gained":[11],"prominence,":[12],"emerging":[13],"as":[14],"an":[15],"important":[16],"method":[17],"to":[18,96],"partially":[19],"replace":[20],"costly":[21],"human":[22],"assessment.However,":[23],"current":[24],"judge":[25,51,68,112],"suffer":[27],"from":[28],"narrow":[29],"specialization":[30],"and":[31,49,60,90,104,113,120,129,133],"limited":[32],"robustness,":[33],"undermining":[34],"their":[35],"capacity":[36],"for":[37,85],"comprehensive":[38],"evaluations.In":[39],"this":[40],"work,":[41],"we":[42],"decompose":[43],"ability":[45],"a":[47,65,75],"generalist":[48,67],"generative":[50],"model":[52,69],"into":[53],"three":[54],"levels:":[55],"objective":[56],"verification,":[57],"subjective":[58],"evaluation,":[59],"rubric":[61],"refinement.We":[62],"present":[63],"CompassJudger-2,":[64],"novel":[66],"that":[70],"overcomes":[71],"these":[72],"limitations":[73],"via":[74],"task-driven,":[76],"multi-scenarios":[77],"data":[78,83,101],"curation":[79],"strategy.We":[80],"conducted":[81],"large-scale":[82],"collection":[84],"each":[86],"type":[87],"task":[89],"designed":[91],"tailored":[92],"rejection":[93],"sampling":[94],"strategies":[95],"filter":[97],"data,":[99],"ensuring":[100],"diversity,":[102],"accuracy,":[103],"effectiveness.Empirically,":[105],"CompassJudger-2":[106],"achieves":[107],"superior":[108],"results":[109],"across":[110],"multiple":[111],"reward":[114],"benchmarks,":[115],"demostrating":[116],"its":[117],"excellent":[118],"robustness":[119],"generalization":[121],"ability.These":[122],"contributions":[123],"advance":[124],"robust,":[125],"scalable":[126],"LLM":[127],"judgment":[128],"establish":[130],"new":[131],"performance":[132],"evaluation":[134],"standards.":[135]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-30T00:00:00"}