{"id":"https://openalex.org/W4392822469","doi":"https://doi.org/10.1145/3589335.3651243","title":"Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform","display_name":"Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4392822469","doi":"https://doi.org/10.1145/3589335.3651243"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3651243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651243","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651243","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054174049","display_name":"Mingyue Cheng","orcid":"https://orcid.org/0000-0001-9873-7681"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyue Cheng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9873-7681","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397003","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-0877-2681"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Data Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0877-2681","affiliations":[{"raw_affiliation_string":"Data Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098953125","display_name":"Jiqian Yang","orcid":"https://orcid.org/0009-0007-6421-2626"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqian Yang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-6421-2626","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453156","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-6956-5550"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6956-5550","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004397982","display_name":"Li Li","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-5491-3693","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007676699","display_name":"Xin Huang","orcid":"https://orcid.org/0009-0001-9775-3046"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Huang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0001-9775-3046","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083808608","display_name":"Liwei Song","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liwei Song","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-7141-6580","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382306","display_name":"Zhi Li","orcid":"https://orcid.org/0000-0002-8061-7486"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Li","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8061-7486","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085496384","display_name":"Zhenya Huang","orcid":"https://orcid.org/0000-0003-1661-0420"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenya Huang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1661-0420","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4835-4102","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1921,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95429365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1035","last_page":"1038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/crowd-sourcing","display_name":"Crowd sourcing","score":0.9028782248497009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.768363356590271},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4126833975315094},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41155701875686646}],"concepts":[{"id":"https://openalex.org/C3018396927","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowd sourcing","level":2,"score":0.9028782248497009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.768363356590271},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4126833975315094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41155701875686646}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3589335.3651243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651243","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651243","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.08305","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.08305","pdf_url":"https://arxiv.org/pdf/2403.08305","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3589335.3651243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3651243","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3651243","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G161133763","display_name":null,"funder_award_id":"2021YFF0901003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2240518327","display_name":null,"funder_award_id":"SC5290005194","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G3594483084","display_name":null,"funder_award_id":"2021YFF0901003","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5510961489","display_name":null,"funder_award_id":"62337001, U20A20229","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5540768979","display_name":null,"funder_award_id":"62337001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6859851492","display_name":null,"funder_award_id":"U20A20229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392822469.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1991055526","https://openalex.org/W2108598243","https://openalex.org/W2335612402","https://openalex.org/W2798881875"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2178843214","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Large":[0],"language":[1,20,53,115,199],"model":[2],"evaluation":[3,70,75,110,158,188],"plays":[4],"a":[5,106,119,175,202],"pivotal":[6],"role":[7],"in":[8,25,126,201],"the":[9,41,69,74,88,93,96,147,165,172],"enhancement":[10],"of":[11,91,142,150,181,193,214],"its":[12,140],"capacity.":[13],"Previously,":[14],"numerous":[15],"methods":[16,57],"for":[17,51,62,113,139,154,206],"evaluating":[18],"large":[19,52,114,198],"models":[21,97,116,128,151,173,200],"have":[22,164],"been":[23],"proposed":[24],"this":[26,161],"area.":[27],"Despite":[28],"their":[29,131,169],"effectiveness,":[30],"these":[31,56,79,102],"existing":[32],"works":[33],"mainly":[34],"focus":[35],"on":[36,130,174],"assessing":[37],"objective":[38],"questions,":[39,170],"overlooking":[40],"capability":[42],"to":[43,86,145,167,196],"evaluate":[44],"subjective":[45],"questions":[46],"which":[47],"is":[48],"extremely":[49],"common":[50],"models.":[54],"Additionally,":[55],"predominantly":[58],"utilize":[59],"centralized":[60,143],"datasets":[61],"evaluation,":[63],"with":[64],"question":[65],"banks":[66],"concentrated":[67],"within":[68],"platforms":[71,80],"themselves.":[72],"Moreover,":[73],"processes":[76],"employed":[77],"by":[78],"often":[81],"overlook":[82],"personalized":[83,176,187],"factors,":[84],"neglecting":[85],"consider":[87],"individual":[89,207],"characteristics":[90],"both":[92],"evaluators":[94],"and":[95,177,210],"being":[98],"evaluated.":[99],"To":[100],"address":[101],"limitations,":[103],"we":[104],"propose":[105],"novel":[107],"anonymous":[108],"crowd-sourcing":[109],"platform,":[111],"BingJian,":[112],"that":[117,204],"employs":[118],"competitive":[120],"scoring":[121],"mechanism":[122],"where":[123],"users":[124,163],"participate":[125],"ranking":[127],"based":[129],"performance.":[132],"This":[133],"platform":[134,185],"stands":[135],"out":[136],"not":[137],"only":[138],"support":[141],"evaluations":[144],"assess":[146,197],"general":[148],"capabilities":[149],"but":[152],"also":[153],"offering":[155],"an":[156],"open":[157],"gateway.":[159],"Through":[160],"gateway,":[162],"opportunity":[166],"submit":[168],"testing":[171],"potentially":[178],"broader":[179],"range":[180],"capabilities.":[182],"Furthermore,":[183],"our":[184],"introduces":[186],"scenarios,":[189],"leveraging":[190],"various":[191],"forms":[192],"human-computer":[194],"interaction":[195],"manner":[203],"accounts":[205],"user":[208],"preferences":[209],"contexts.":[211],"The":[212],"demonstration":[213],"BingJian":[215],"can":[216],"be":[217],"accessed":[218],"at":[219],"https://github.com/Mingyue-Cheng/Bingjian.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2024-03-15T00:00:00"}
