{"id":"https://openalex.org/W7150752175","doi":"https://doi.org/10.48550/arxiv.2604.02368","title":"Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation","display_name":"Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7150752175","doi":"https://doi.org/10.48550/arxiv.2604.02368"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.02368","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.02368","pdf_url":"https://arxiv.org/pdf/2604.02368","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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/2604.02368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123528195","display_name":"Xue Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133046382","display_name":"Xin Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133034259","display_name":"Yuxin Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133009629","display_name":"Yongchang Peng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yongchang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133054696","display_name":"Duo Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Duo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020661044","display_name":"Zhoufutu Wen","orcid":"https://orcid.org/0009-0000-0894-5824","observed_orcids":["https://orcid.org/0009-0000-0894-5824"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Zhoufutu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133004963","display_name":"Ge Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133055385","display_name":"Kaiyuan Zhang","orcid":"https://orcid.org/0009-0006-7866-6920","observed_orcids":["https://orcid.org/0009-0006-7866-6920"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133022113","display_name":"Xinyu Chen","orcid":"https://orcid.org/0009-0001-1584-1174","observed_orcids":["https://orcid.org/0009-0001-1584-1174"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036376607","display_name":"Yida Ding","orcid":"https://orcid.org/0009-0009-3137-8675","observed_orcids":["https://orcid.org/0009-0009-3137-8675"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133019709","display_name":"Tianci He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Tianci","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133019879","display_name":"Liang Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Jiani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133019879","display_name":"Liang Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133061861","display_name":"Ziyun Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Ziyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133025361","display_name":"Yongzhe Hui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui, Yongzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158111264","display_name":"Jianpeng Jiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Jianpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133062106","display_name":"Chennan Ju","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju, Chennan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108311306","display_name":"Yingru Kong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Yingru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134403181","display_name":"Yiran Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144323017","display_name":"Jiashuo Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiashuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144332196","display_name":"Mengyun Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Mengyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133032952","display_name":"Luyao Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Luyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133049275","display_name":"Fei Ni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144385616","display_name":"Yiqing Ni","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Yiqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144333280","display_name":"Pengbo Niu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Pengbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104181719","display_name":"Yueyan Qiu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Yueyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133022240","display_name":"Yanle Ren","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Yanle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144353082","display_name":"Xinyu Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144360414","display_name":"Zilin Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Zilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128645777","display_name":"Zaiyuan Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zaiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133056721","display_name":"Wenjie Yue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144317647","display_name":"Chun Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146875933","display_name":"Shiyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133259838","display_name":"Xinyi Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xinyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017926053","display_name":"Kaiwen Zhao","orcid":"https://orcid.org/0009-0005-2868-8147","observed_orcids":["https://orcid.org/0009-0005-2868-8147"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Kaiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133034752","display_name":"Zhenwei Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhenwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134394343","display_name":"Shanshan Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shanshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146646330","display_name":"Qi Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148931907","display_name":"Wenhao Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wenhao","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":false,"cited_by_count":0,"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/T10028","display_name":"Topic Modeling","score":0.8720999956130981,"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/T10028","display_name":"Topic Modeling","score":0.8720999956130981,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.027499999850988388,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.02449999935925007,"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/llm-evaluation","display_name":"LLM evaluation","score":0.6729999780654907},{"id":"https://openalex.org/keywords/rubric-based-assessment","display_name":"rubric-based assessment","score":0.8690000176429749},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.7699999809265137},{"id":"https://openalex.org/keywords/professional-domains","display_name":"professional domains","score":0.5479999780654907},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.4020000100135803},{"id":"https://openalex.org/keywords/ecological-validity","display_name":"ecological validity","score":0.5139999985694885}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.8603000044822693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147000193595886},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.5227000117301941},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C2775987171","wikidata":"https://www.wikidata.org/wiki/Q192797","display_name":"Elite","level":3,"score":0.4320000112056732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26809999346733093},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.02368","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.02368","pdf_url":"https://arxiv.org/pdf/2604.02368","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.02368","doi":"https://doi.org/10.48550/arxiv.2604.02368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.02368","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:2604.02368","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.02368","pdf_url":"https://arxiv.org/pdf/2604.02368","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416157540","https://openalex.org/W4416245719","https://openalex.org/W6929123975","https://openalex.org/W7167626665","https://openalex.org/W4417134182","https://openalex.org/W4405095313","https://openalex.org/W7134817938","https://openalex.org/W7138982173","https://openalex.org/W6979306079","https://openalex.org/W7164153315"],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3,174],"(LLMs)":[4],"exhibit":[5,176],"plateauing":[6],"performance":[7,155],"on":[8,34],"conventional":[9],"benchmarks,":[10],"a":[11,47,129,153,161,169,191,202],"pivotal":[12],"challenge":[13],"persists:":[14],"evaluating":[15],"their":[16],"proficiency":[17],"in":[18,182,194],"complex,":[19],"open-ended":[20],"tasks":[21,64,81],"characterizing":[22],"genuine":[23],"expert-level":[24],"cognition.":[25],"Existing":[26],"frameworks":[27],"suffer":[28],"from":[29,84,92,209],"narrow":[30],"domain":[31,89],"coverage,":[32],"reliance":[33],"generalist":[35],"tasks,":[36],"or":[37,100],"self-evaluation":[38],"biases.":[39,145],"To":[40,120],"bridge":[41],"this":[42],"gap,":[43],"we":[44,126],"present":[45],"XpertBench,":[46],"high-fidelity":[48],"benchmark":[49],"engineered":[50],"to":[51,116,142,212],"assess":[52,117],"LLMs":[53,151],"across":[54,65],"authentic":[55],"professional":[56,118,214],"domains.":[57],"XpertBench":[58,200],"consists":[59],"of":[60,149,165],"1,346":[61],"meticulously":[62],"curated":[63],"80":[66],"categories,":[67],"spanning":[68],"finance,":[69],"healthcare,":[70],"legal":[71],"services,":[72],"education,":[73],"and":[74,78,95,198],"dual-track":[75],"research":[76],"(STEM":[77],"Humanities).":[79],"These":[80,188],"are":[82],"derived":[83],"over":[85],"1,000":[86],"submissions":[87],"by":[88],"experts--including":[90],"researchers":[91],"elite":[93],"institutions":[94],"practitioners":[96],"with":[97,111,138,168],"extensive":[98],"clinical":[99],"industrial":[101],"experience--ensuring":[102],"superior":[103],"ecological":[104],"validity.":[105],"Each":[106],"task":[107],"uses":[108],"detailed":[109],"rubrics":[110],"mostly":[112],"15-40":[113],"weighted":[114],"checkpoints":[115],"rigor.":[119],"facilitate":[121],"scalable":[122],"yet":[123],"human-aligned":[124],"assessment,":[125],"introduce":[127],"ShotJudge,":[128],"novel":[130],"evaluation":[131,148],"paradigm":[132],"that":[133],"employs":[134],"LLM":[135],"judges":[136],"calibrated":[137],"expert":[139],"few-shot":[140],"exemplars":[141],"mitigate":[143],"self-rewarding":[144],"Our":[146],"empirical":[147],"state-of-the-art":[150],"reveals":[152],"pronounced":[154],"ceiling:":[156],"even":[157],"leading":[158],"models":[159],"achieve":[160],"peak":[162],"success":[163],"rate":[164],"only":[166],"~66%,":[167],"mean":[170],"score":[171],"around":[172],"55%.":[173],"also":[175],"domain-specific":[177],"divergence,":[178],"showing":[179],"non-overlapping":[180],"strengths":[181],"quantitative":[183],"reasoning":[184],"versus":[185],"linguistic":[186],"synthesis..":[187],"findings":[189],"underscore":[190],"significant":[192],"\"expert-gap\"":[193],"current":[195],"AI":[196],"systems":[197],"establish":[199],"as":[201],"critical":[203],"instrument":[204],"for":[205],"navigating":[206],"the":[207],"transition":[208],"general-purpose":[210],"assistants":[211],"specialized":[213],"collaborators.":[215]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-04-07T00:00:00"}