{"id":"https://openalex.org/W4412945504","doi":"https://doi.org/10.18653/v1/2025.acl-long.437","title":"SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation","display_name":"SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945504","doi":"https://doi.org/10.18653/v1/2025.acl-long.437"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.437","pdf_url":"https://aclanthology.org/2025.acl-long.437.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.437.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114033608","display_name":"Yufei Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufei Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102793227","display_name":"Jiao Sun","orcid":"https://orcid.org/0000-0001-9279-4802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030248499","display_name":"Nanyun Peng","orcid":"https://orcid.org/0000-0002-8509-6595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanyun Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028973552","display_name":"Zizhao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zizhao Zhang","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8917","last_page":"8933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.8543999791145325,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.8543999791145325,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8113999962806702,"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/T13999","display_name":"Digital Rights Management and Security","score":0.7766000032424927,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/tree","display_name":"Tree (set theory)","score":0.5373519659042358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4897923469543457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09069272875785828}],"concepts":[{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5373519659042358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4897923469543457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09069272875785828},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.437","pdf_url":"https://aclanthology.org/2025.acl-long.437.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.437","pdf_url":"https://aclanthology.org/2025.acl-long.437.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945504.pdf","grobid_xml":"https://content.openalex.org/works/W4412945504.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":{"As":[0],"language":[1],"models":[2],"evolve":[3],"to":[4,14,27,79,107],"tackle":[5],"complex":[6],"and":[7,60,113],"multifaceted":[8],"tasks,":[9],"their":[10],"evaluation":[11],"must":[12],"adapt":[13],"capture":[15],"this":[16,33],"intricacy.A":[17],"granular,":[18],"skillspecific":[19],"understanding":[20,44],"of":[21,74,82,84],"model":[22,30,45,58,98,118],"capabilities":[23],"can":[24],"empower":[25],"researchers":[26],"make":[28],"informed":[29],"development":[31],"plans.In":[32],"paper,":[34],"we":[35],"introduce":[36],"SKILLVERSE,":[37],"an":[38],"unsupervised":[39],"treestructured":[40],"diagnosis":[41],"framework":[42],"for":[43],"proficiency":[46,70],"in":[47,92],"specific":[48],"abilities.With":[49],"LLM":[50],"as":[51],"a":[52,65,104,121],"judge,":[53],"SKILLVERSE":[54,76],"first":[55],"critiques":[56],"the":[57,128],"responses,":[59],"then":[61],"organizes":[62],"them":[63],"into":[64],"hierarchical":[66],"structure":[67],"termed":[68],"dendrogram.Given":[69],"at":[71],"arbitrary":[72],"levels":[73],"granularity,":[75],"is":[77],"flexible":[78],"produce":[80],"insights":[81],"behaviors":[83],"modern":[85],"large":[86],"models.We":[87],"also":[88],"demonstrate":[89],"its":[90],"efficacy":[91],"two":[93],"downstream":[94],"tasks:":[95],"1)":[96],"improving":[97],"in-context":[99],"learning":[100],"by":[101],"25%":[102],"using":[103],"tree-search":[105],"algorithm":[106],"select":[108],"more":[109],"informative":[110],"few":[111],"shots,":[112],"2)":[114],"accurately":[115],"predicting":[116],"new":[117],"weaknesses":[119],"with":[120],"55%":[122],"success":[123],"rate,":[124],"22%":[125],"higher":[126],"than":[127],"baseline.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}