{"id":"https://openalex.org/W4409918512","doi":"https://doi.org/10.1145/3732784","title":"TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs","display_name":"TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs","publication_year":2025,"publication_date":"2025-04-29","ids":{"openalex":"https://openalex.org/W4409918512","doi":"https://doi.org/10.1145/3732784"},"language":"en","primary_location":{"id":"doi:10.1145/3732784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3732784","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113530009","display_name":"Shu Fei Xie","orcid":"https://orcid.org/0009-0005-8037-4700"},"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":"Shuyi Xie","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-8037-4700","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024873469","display_name":"Wenlin Yao","orcid":"https://orcid.org/0000-0002-4502-0350"},"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"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wenlin Yao","raw_affiliation_strings":["Tencent AI Lab, Seattle, Washington, USA","Tencent AI Lab, Seattle, US"],"raw_orcid":"https://orcid.org/0000-0002-4502-0350","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Seattle, Washington, USA","institution_ids":[]},{"raw_affiliation_string":"Tencent AI Lab, Seattle, US","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046017342","display_name":"Yong Dai","orcid":"https://orcid.org/0000-0002-3041-5851"},"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":"Yong Dai","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China","Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3041-5851","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaobo Wang","orcid":"https://orcid.org/0009-0007-2106-693X"},"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":"Shaobo Wang","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-2106-693X","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zishan Xu","orcid":"https://orcid.org/0009-0009-4661-8918"},"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":"Zishan Xu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-4661-8918","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Lin","orcid":"https://orcid.org/0009-0003-4461-1954"},"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"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Lin","raw_affiliation_strings":["Southeast University, Nanjing, China and Tencent, Shenzhen, China","Tencent, Shenzhen, China & Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-4461-1954","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China and Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I76569877"]},{"raw_affiliation_string":"Tencent, Shenzhen, China & Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073801367","display_name":"Donglin Zhou","orcid":"https://orcid.org/0000-0001-5987-646X"},"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":"Donglin Zhou","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5987-646X","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013847092","display_name":"Lifeng Jin","orcid":"https://orcid.org/0000-0002-6754-7014"},"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"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Lifeng Jin","raw_affiliation_strings":["Tencent AI Lab, Seattle, Washington, USA","Tencent AI Lab, Seattle, US"],"raw_orcid":"https://orcid.org/0000-0002-6754-7014","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Seattle, Washington, USA","institution_ids":[]},{"raw_affiliation_string":"Tencent AI Lab, Seattle, US","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100557597","display_name":"Xinhua Feng","orcid":null},"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":"Xinhua Feng","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-2061-0175","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074357324","display_name":"Pengzhi Wei","orcid":"https://orcid.org/0000-0001-9299-0862"},"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":"Pengzhi Wei","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-3709-378X","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113753366","display_name":"Yujie Lin","orcid":"https://orcid.org/0009-0009-9232-0506"},"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":"Yujie Lin","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-9232-0506","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhichao Hu","orcid":"https://orcid.org/0009-0008-6626-7337"},"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":"Zhichao Hu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-6626-7337","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Seattle, Washington, USA","Tencent AI Lab, Seattle, US"],"raw_orcid":"https://orcid.org/0000-0003-0520-6844","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Seattle, Washington, USA","institution_ids":[]},{"raw_affiliation_string":"Tencent AI Lab, Seattle, US","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058849717","display_name":"Zhengyou Zhang","orcid":"https://orcid.org/0000-0002-6606-2525"},"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"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhengyou Zhang","raw_affiliation_strings":["Tencent AI Lab, Seattle, Washington, USA","Tencent AI Lab, Seattle, US"],"raw_orcid":"https://orcid.org/0000-0002-6606-2525","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Seattle, Washington, USA","institution_ids":[]},{"raw_affiliation_string":"Tencent AI Lab, Seattle, US","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103719516","display_name":"Jing Nie","orcid":null},"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":"Jing Nie","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-4334-1937","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuhong Liu","orcid":"https://orcid.org/0009-0005-9083-4977"},"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":"Yuhong Liu","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-9083-4977","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0328955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"4","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9860000014305115,"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/computer-science","display_name":"Computer science","score":0.8206839561462402},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39063701033592224},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3373386859893799}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206839561462402},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39063701033592224},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3373386859893799}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3732784","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3732784","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W3011574394","https://openalex.org/W3088409176","https://openalex.org/W3185341429","https://openalex.org/W4221143046"],"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":[1,11],"models":[2],"(LLMs)":[3],"have":[4,165,178],"shown":[5],"impressive":[6],"capabilities":[7,65],"across":[8],"various":[9],"natural":[10],"tasks.":[12,43],"However,":[13],"evaluating":[14],"their":[15],"alignment":[16,126],"with":[17,144],"human":[18,30,99,125],"preferences":[19],"remains":[20],"a":[21,28,46,80,120,145,152],"challenge.":[22],"To":[23],"this":[24],"end,":[25],"we":[26,194],"propose":[27],"comprehensive":[29,81],"evaluation":[31,89,143,175],"framework":[32,150],"to":[33,76,93,123,196],"assess":[34],"LLMs\u2019":[35],"proficiency":[36],"in":[37,79,127,183,202],"following":[38],"instructions":[39],"on":[40],"diverse":[41,64],"real-world":[42,162],"We":[44,85,134,164],"construct":[45],"hierarchical":[47],"task":[48,170],"tree":[49],"encompassing":[50],"seven":[51],"major":[52],"areas":[53],"covering":[54],"over":[55,59,105],"200":[56],"categories":[57],"and":[58,73,82,91,114,132,174,207],"800":[60],"tasks,":[61],"which":[62,177],"covers":[63],"such":[66],"as":[67,157,181],"question":[68],"answering,":[69],"reasoning,":[70],"multi-turn":[71],"dialogue,":[72],"text":[74],"generation,":[75],"evaluate":[77,124],"LLMs":[78,128,156],"in-depth":[83],"manner.":[84],"also":[86,135],"design":[87],"detailed":[88],"standards":[90],"processes":[92],"facilitate":[94,197],"consistent,":[95],"unbiased":[96],"judgments":[97],"from":[98],"evaluators.":[100],"A":[101],"test":[102],"set":[103],"of":[104,139,142,155,187,200,205],"3,000":[106],"instances":[107],"is":[108],"released,":[109],"spanning":[110],"different":[111],"difficulty":[112],"levels":[113],"knowledge":[115],"domains.":[116],"Our":[117,149],"work":[118],"provides":[119],"standardized":[121],"methodology":[122,176],"for":[129],"both":[130],"English":[131],"Chinese.":[133],"analyze":[136],"the":[137,169,185,198,203],"feasibility":[138],"automating":[140],"parts":[141],"strong":[146],"LLM":[147],"(GPT-4).":[148],"supports":[151],"thorough":[153],"assessment":[154],"they":[158],"are":[159],"integrated":[160],"into":[161],"applications.":[163],"made":[166],"publicly":[167],"available":[168],"tree,":[171],"TencentLLMEval":[172],"dataset,":[173],"been":[179],"demonstrated":[180],"effective":[182],"assessing":[184],"performance":[186],"Tencent":[188],"Hunyuan":[189],"LLMs.":[190,209],"By":[191],"doing":[192],"so,":[193],"aim":[195],"benchmarking":[199],"advances":[201],"development":[204],"safe":[206],"human-aligned":[208]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}