{"id":"https://openalex.org/W4409362589","doi":"https://doi.org/10.1609/aaai.v39i23.34627","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","display_name":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409362589","doi":"https://doi.org/10.1609/aaai.v39i23.34627"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i23.34627","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i23.34627","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34627/36782","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34627/36782","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100642169","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-5555-0734"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090588589","display_name":"Yunshi Lan","orcid":"https://orcid.org/0000-0002-0192-8498"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunshi Lan","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072105113","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0002-3763-5080"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Chao Yang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6591,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7969696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"39","issue":"23","first_page":"24485","last_page":"24493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9390000104904175,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9390000104904175,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8035835027694702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6185747981071472},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.536942720413208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3226391673088074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14443013072013855},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12444576621055603},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06363865733146667}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8035835027694702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6185747981071472},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.536942720413208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3226391673088074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14443013072013855},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12444576621055603},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06363865733146667},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v39i23.34627","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i23.34627","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34627/36782","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/34627","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/34627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i23.34627","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i23.34627","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34627/36782","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409362589.pdf","grobid_xml":"https://content.openalex.org/works/W4409362589.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/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Recently,":[0],"numerous":[1],"new":[2],"benchmarks":[3],"have":[4],"been":[5],"established":[6],"to":[7,37,84,105,153],"evaluate":[8,122],"the":[9,38,42,74,101,107,113,118,137,155],"performance":[10],"of":[11,41,89,117,125,159],"large":[12],"language":[13],"models":[14,124],"(LLMs)":[15],"via":[16],"either":[17],"computing":[18],"a":[19,27,55,63,87,92,95],"holistic":[20],"score":[21],"or":[22],"employing":[23],"another":[24],"LLM":[25,65,79],"as":[26,81],"judge.":[28],"However,":[29],"these":[30],"approaches":[31],"suffer":[32],"from":[33],"data":[34,75],"leakage":[35],"due":[36],"open":[39],"access":[40],"benchmark":[43],"and":[44,71,111,115,132,134,157],"inflexible":[45],"evaluation":[46,57,69,103,119],"process.":[47,120],"To":[48],"address":[49],"this":[50,78],"issue,":[51],"we":[52],"introduce":[53],"TreeEval,":[54],"benchmark-free":[56],"method":[58],"for":[59],"LLMs":[60],"that":[61],"let":[62],"high-performance":[64],"host":[66],"an":[67,82],"irreproducible":[68],"session":[70],"essentially":[72],"avoids":[73],"leakage.":[76],"Moreover,":[77],"performs":[80],"examiner":[83],"raise":[85],"up":[86],"series":[88],"questions":[90],"under":[91],"topic":[93],"with":[94,141],"tree":[96],"planing":[97],"strategy,":[98],"which":[99],"considers":[100],"current":[102],"status":[104],"decide":[106],"next":[108],"question":[109],"generation":[110],"ensures":[112],"completeness":[114],"efficiency":[116],"We":[121,148],"6":[123],"different":[126],"parameter":[127],"sizes,":[128],"including":[129],"7B,":[130],"13B,":[131],"34B,":[133],"ultimately":[135],"achieved":[136],"highest":[138],"correlation":[139],"coefficient":[140],"AlpacaEval2.0":[142],"using":[143],"only":[144],"around":[145],"45":[146],"questions.":[147],"also":[149],"conduct":[150],"more":[151],"analysis":[152],"show":[154],"robustness":[156],"reliability":[158],"TreeEval.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}