{"id":"https://openalex.org/W4403788992","doi":"https://doi.org/10.48550/arxiv.2409.16202","title":"CJEval: A Benchmark for Assessing Large Language Models Using Chinese Junior High School Exam Data","display_name":"CJEval: A Benchmark for Assessing Large Language Models Using Chinese Junior High School Exam Data","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4403788992","doi":"https://doi.org/10.48550/arxiv.2409.16202"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.16202","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16202","pdf_url":"https://arxiv.org/pdf/2409.16202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.16202","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100766231","display_name":"Qianwen Zhang","orcid":"https://orcid.org/0009-0000-2637-7314","observed_orcids":["https://orcid.org/0009-0000-2637-7314"]},"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":"Zhang, Qian-Wen","raw_affiliation_strings":["Tencent YouTu Lab ,","{cowenzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab ,","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{cowenzhang ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645299","display_name":"Haochen Wang","orcid":"https://orcid.org/0000-0003-1191-6682","observed_orcids":["https://orcid.org/0000-0003-1191-6682"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Haochen","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777304","display_name":"Fang Li","orcid":"https://orcid.org/0000-0003-0371-1687","observed_orcids":["https://orcid.org/0000-0003-0371-1687"]},"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":"Li, Fang","raw_affiliation_strings":["Tencent YouTu Lab ,","{cowenzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab ,","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{cowenzhang ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"An, Siyu","orcid":null,"observed_orcids":[]},"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":"An, Siyu","raw_affiliation_strings":["Tencent YouTu Lab ,","{cowenzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab ,","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{cowenzhang ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069607513","display_name":"Lingfeng Qiao","orcid":"https://orcid.org/0000-0002-4164-2822","observed_orcids":["https://orcid.org/0000-0002-4164-2822"]},"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":"Qiao, Lingfeng","raw_affiliation_strings":["Tencent YouTu Lab ,","{cowenzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab ,","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{cowenzhang ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004474713","display_name":"Liangcai Gao","orcid":"https://orcid.org/0000-0001-9444-1568","observed_orcids":["https://orcid.org/0000-0001-9444-1568"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Liangcai","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567807","display_name":"Di Yin","orcid":null,"observed_orcids":[]},"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":"Yin, Di","raw_affiliation_strings":["Tencent YouTu Lab ,","{cowenzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab ,","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{cowenzhang ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110860333","display_name":"Xing Sun","orcid":null,"observed_orcids":[]},"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":"Sun, Xing","raw_affiliation_strings":["Tencent YouTu Lab ,","{cowenzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab ,","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"{cowenzhang ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14414","display_name":"Artificial Intelligence in Education","score":0.48559999465942383,"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/T14414","display_name":"Artificial Intelligence in Education","score":0.48559999465942383,"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":0.22450000047683716,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.2078000009059906,"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/large-language-models","display_name":"large language models","score":0.9290000200271606},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.47699999809265137},{"id":"https://openalex.org/keywords/examination-evaluation","display_name":"exam evaluation","score":0.640999972820282},{"id":"https://openalex.org/keywords/online-learning-platforms","display_name":"online learning platforms","score":0.7089999914169312},{"id":"https://openalex.org/keywords/educational-tasks","display_name":"educational tasks","score":0.41999998688697815},{"id":"https://openalex.org/keywords/answer-explanations","display_name":"answer explanations","score":0.7860000133514404},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.7979999780654907},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.3919999897480011}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7393231391906738},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.5455054044723511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4911055564880371},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.41177898645401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4079664647579193},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38801276683807373},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2252849042415619},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.14320290088653564},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1127101480960846},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.050403892993927}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.16202","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16202","pdf_url":"https://arxiv.org/pdf/2409.16202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.16202","doi":"https://doi.org/10.48550/arxiv.2409.16202","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.16202","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.16202","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16202","pdf_url":"https://arxiv.org/pdf/2409.16202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.975600004196167,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403788992.pdf","grobid_xml":"https://content.openalex.org/works/W4403788992.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416933269","https://openalex.org/W7103144980","https://openalex.org/W4391376649","https://openalex.org/W6979307719","https://openalex.org/W4414930418","https://openalex.org/W4393153185","https://openalex.org/W4410636878","https://openalex.org/W6910917485","https://openalex.org/W7204498164","https://openalex.org/W7138984503"],"abstract_inverted_index":{"Online":[0],"education":[1],"platforms":[2],"have":[3,144],"significantly":[4],"transformed":[5],"the":[6,19,25,34,146,154],"dissemination":[7],"of":[8,22,27,37,83,131,150,156],"educational":[9,55,89,138],"resources":[10],"by":[11,134],"providing":[12],"a":[13,71,128],"dynamic":[14],"and":[15,100,114,126,142,148],"digital":[16],"infrastructure.":[17],"With":[18],"further":[20],"enhancement":[21],"this":[23,66,119],"transformation,":[24],"advent":[26],"Large":[28],"Language":[29],"Models":[30],"(LLMs)":[31],"has":[32],"elevated":[33],"intelligence":[35],"levels":[36],"these":[38],"platforms.":[39],"However,":[40],"current":[41],"academic":[42],"benchmarks":[43],"provide":[44],"limited":[45],"guidance":[46],"for":[47],"real-world":[48],"industry":[49],"scenarios.":[50],"This":[51],"limitation":[52],"arises":[53],"because":[54],"applications":[56,125],"require":[57],"more":[58],"than":[59],"mere":[60],"test":[61],"question":[62,108],"responses.":[63],"To":[64],"bridge":[65],"gap,":[67],"we":[68,121],"introduce":[69],"CJEval,":[70],"benchmark":[72],"based":[73],"on":[74,136],"Chinese":[75],"Junior":[76],"High":[77],"School":[78],"Exam":[79],"Evaluations.":[80],"CJEval":[81],"consists":[82],"26,136":[84],"samples":[85,95],"across":[86],"four":[87],"application-level":[88],"tasks":[90],"covering":[91],"ten":[92],"subjects.":[93],"These":[94],"include":[96],"not":[97],"only":[98],"questions":[99],"answers":[101],"but":[102],"also":[103],"detailed":[104],"annotations":[105],"such":[106],"as":[107],"types,":[109],"difficulty":[110],"levels,":[111],"knowledge":[112],"concepts,":[113],"answer":[115],"explanations.":[116],"By":[117],"utilizing":[118],"benchmark,":[120],"assessed":[122],"LLMs'":[123],"potential":[124],"conducted":[127],"comprehensive":[129],"analysis":[130],"their":[132],"performance":[133],"fine-tuning":[135],"various":[137],"tasks.":[139],"Extensive":[140],"experiments":[141],"discussions":[143],"highlighted":[145],"opportunities":[147],"challenges":[149],"applying":[151],"LLMs":[152],"in":[153],"field":[155],"education.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-10-27T00:00:00"}