{"id":"https://openalex.org/W7166873985","doi":"https://doi.org/10.18653/v1/2026.findings-acl.631","title":"From Mimesis to Metamorphosis: Evolving VLM Judges via In-Context Comparing and Knowledge Internalization","display_name":"From Mimesis to Metamorphosis: Evolving VLM Judges via In-Context Comparing and Knowledge Internalization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166873985","doi":"https://doi.org/10.18653/v1/2026.findings-acl.631"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.631","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.631","pdf_url":"https://aclanthology.org/2026.findings-acl.631.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.631.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031277837","display_name":"Juntuo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juntuo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113062347","display_name":"Yuming Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuming Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139718165","display_name":"Yifan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088111426","display_name":"Lunxi Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lunxi Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139828190","display_name":"Liang Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139729823","display_name":"Dan Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Meng","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93881453,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12957","last_page":"12971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.18529999256134033,"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":0.18529999256134033,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.15379999577999115,"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/T14013","display_name":"Legal Language and Interpretation","score":0.03790000081062317,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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/internalization","display_name":"Internalization","score":0.40880000591278076},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3328000009059906},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3237000107765198},{"id":"https://openalex.org/keywords/criticism","display_name":"Criticism","score":0.2969000041484833},{"id":"https://openalex.org/keywords/agency","display_name":"Agency (philosophy)","score":0.29589998722076416},{"id":"https://openalex.org/keywords/interrogation","display_name":"Interrogation","score":0.27619999647140503}],"concepts":[{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.41940000653266907},{"id":"https://openalex.org/C139770010","wikidata":"https://www.wikidata.org/wiki/Q1339807","display_name":"Internalization","level":3,"score":0.40880000591278076},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3587000072002411},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C7991579","wikidata":"https://www.wikidata.org/wiki/Q17955","display_name":"Criticism","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.27790001034736633},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26420000195503235},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.260699987411499}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.631","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.631","pdf_url":"https://aclanthology.org/2026.findings-acl.631.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.631","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.631","pdf_url":"https://aclanthology.org/2026.findings-acl.631.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166873985.pdf","grobid_xml":"https://content.openalex.org/works/W7166873985.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"are":[3],"increasingly":[4],"adopted":[5],"as":[6,43,101],"judges":[7],"for":[8,139],"subjective":[9,41],"assessment,":[10],"yet":[11],"absolute":[12],"scoring":[13],"remains":[14],"brittle":[15],"due":[16],"to":[17,52,63,67,121],"inconsistent":[18],"scales":[19],"and":[20,142],"inherent":[21],"preference":[22],"biases.To":[23],"bridge":[24],"this":[25,90],"gap,":[26],"we":[27,57],"propose":[28],"S":[29,112],"2":[30,88,113],"AD":[31,114],"(Semantic-Anchored":[32],"Scale-Agnostic":[33],"Distillation),":[34],"a":[35,69,76,102],"novel":[36],"easy-to-hard":[37],"framework":[38,125],"that":[39,80,119],"operationalizes":[40],"assessment":[42],"comparative":[44,91,137],"analysis,":[45],"conceptualizing":[46],"the":[47,65,133],"judge's":[48],"evolution":[49],"from":[50],"mimesis":[51],"metamorphosis.In":[53],"Stage":[54,87],"1":[55],"(Mimesis),":[56],"introduce":[58],"Dynamic":[59],"Soft":[60],"Positioning":[61],"(DSP)":[62],"train":[64],"judge":[66],"compare":[68],"query":[70],"against":[71],"retrieved":[72],"reference":[73],"images,":[74],"establishing":[75],"relative":[77],"evaluation":[78],"space":[79],"ensures":[81],"consistent":[82],"ordering":[83],"under":[84],"heterogeneous":[85],"scales.In":[86],"(Metamorphosis),":[89],"capability":[92],"is":[93],"internalized":[94,136],"via":[95],"Language":[96],"Buttons-discrete":[97],"semantic":[98],"levels":[99],"serving":[100],"retrieval-free":[103],"internal":[104],"reference.Optimized":[105],"with":[106],"Group":[107],"Relative":[108],"Policy":[109],"Optimization":[110],"(GRPO),":[111],"achieves":[115],"efficient,":[116],"scale-steerable":[117,143],"inference":[118],"adapts":[120],"diverse":[122],"grading":[123],"standards.Our":[124],"reaches":[126],"state-of-the-art":[127],"performance":[128],"across":[129],"multiple":[130],"benchmarks,":[131],"validating":[132],"effectiveness":[134],"of":[135],"priors":[138],"robust,":[140],"rank-invariant,":[141],"evaluation.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}