{"id":"https://openalex.org/W4412888329","doi":"https://doi.org/10.18653/v1/2025.findings-acl.494","title":"Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework","display_name":"Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888329","doi":"https://doi.org/10.18653/v1/2025.findings-acl.494"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.494","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.494","pdf_url":"https://aclanthology.org/2025.findings-acl.494.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 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.494.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050343206","display_name":"Kaishuai Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaishuai Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081246075","display_name":"Tiezheng Yu","orcid":"https://orcid.org/0000-0001-5396-950X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiezheng Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070207133","display_name":"Yi Cheng","orcid":"https://orcid.org/0000-0002-5963-5751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917828","display_name":"Wenjun Hou","orcid":"https://orcid.org/0000-0001-9747-5894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjun Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038537171","display_name":"Liangyou Li","orcid":"https://orcid.org/0000-0002-0279-003X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangyou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086603207","display_name":"Xin Jiang","orcid":"https://orcid.org/0000-0002-9117-8247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046228314","display_name":"Lifeng Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifeng Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426167","display_name":"Qun Liu","orcid":"https://orcid.org/0000-0002-6329-3096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qun Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100408989","display_name":"Wenjie Li","orcid":"https://orcid.org/0000-0003-2717-9031"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"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":0.20514089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9488","last_page":"9502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12010","display_name":"Evaluation and Performance Assessment","score":0.9162999987602234,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12010","display_name":"Evaluation and Performance Assessment","score":0.9162999987602234,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6800169944763184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6800169944763184}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.494","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.494","pdf_url":"https://aclanthology.org/2025.findings-acl.494.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.494","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.494","pdf_url":"https://aclanthology.org/2025.findings-acl.494.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888329.pdf","grobid_xml":"https://content.openalex.org/works/W4412888329.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,40],"being":[5],"used":[6],"more":[7,9],"and":[8,29,57,65,83,87,106,112,135,153,162],"extensively":[10],"for":[11,54,129],"automated":[12],"evaluation":[13,27,75,81,104,130,161,167],"in":[14,51,60,151,165],"various":[15],"scenarios.Previous":[16],"studies":[17],"have":[18],"attempted":[19],"to":[20,24,43,63,90,116,139],"fine-tune":[21],"open-source":[22],"LLMs":[23],"replicate":[25],"the":[26,118,141,157],"explanations":[28],"judgments":[30],"of":[31,95,159],"powerful":[32],"proprietary":[33],"models,":[34],"such":[35],"as":[36],"GPT-4.However,":[37],"these":[38,69],"methods":[39],"largely":[41],"limited":[42],"text-based":[44,86,134],"analyses":[45,89,105,115,164],"under":[46],"predefined":[47],"general":[48],"criteria,":[49],"resulting":[50],"reduced":[52],"adaptability":[53],"unseen":[55],"instructions":[56],"demonstrating":[58],"instability":[59],"evaluating":[61],"adherence":[62],"quantitative":[64],"structural":[66],"constraints.To":[67],"address":[68],"limitations,":[70],"we":[71],"propose":[72],"a":[73,98,107,122],"novel":[74],"framework,":[76],"ARJudge,":[77],"that":[78,101,110,126,145],"adaptively":[79],"formulates":[80],"criteria":[82,131],"synthesizes":[84],"both":[85],"code-driven":[88,136,163],"evaluate":[91],"LLM":[92],"responses.ARJudge":[93],"consists":[94],"two":[96],"components:":[97],"fine-tuned":[99,149],"Analyzer":[100],"generates":[102],"multi-faceted":[103,160],"tuning-free":[108],"Refiner":[109],"combines":[111],"refines":[113],"all":[114],"make":[117],"final":[119],"judgment.We":[120],"construct":[121],"Composite":[123],"Analysis":[124],"Corpus":[125],"integrates":[127],"tasks":[128],"generation":[132,138],"alongside":[133],"analysis":[137],"train":[140],"Analyzer.Our":[142],"results":[143],"demonstrate":[144],"ARJudge":[146],"outperforms":[147],"existing":[148],"evaluators":[150],"effectiveness":[152],"robustness.Furthermore,":[154],"it":[155],"demonstrates":[156],"importance":[158],"enhancing":[166],"capabilities.":[168]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}