{"id":"https://openalex.org/W4416018126","doi":"https://doi.org/10.1145/3746252.3761604","title":"C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation","display_name":"C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416018126","doi":"https://doi.org/10.1145/3746252.3761604"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-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/A5011841326","display_name":"Xu Zhang","orcid":"https://orcid.org/0009-0003-4899-9060"},"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":true,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047699551","display_name":"Zhifei Liu","orcid":"https://orcid.org/0009-0003-2255-9681"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifei Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111350279","display_name":"Jiahao Wang","orcid":"https://orcid.org/0000-0002-6657-6403"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Wang","raw_affiliation_strings":["Trustworthy Technology and Engineering Laboratory, Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Trustworthy Technology and Engineering Laboratory, Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085576021","display_name":"Huixuan Zhang","orcid":"https://orcid.org/0009-0009-2354-723X"},"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":"Huixuan Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112352375","display_name":"Fan Xu","orcid":"https://orcid.org/0009-0007-8632-6288"},"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":"Fan Xu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051262853","display_name":"J. Zhang","orcid":"https://orcid.org/0009-0004-0083-2584"},"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":"Junzhe Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029568096","display_name":"Xiaojun Wan","orcid":"https://orcid.org/0000-0001-6887-1994"},"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":"Xiaojun Wan","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5011841326"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17580641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6575","last_page":"6579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3352999985218048,"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":0.3352999985218048,"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/T12488","display_name":"Mental Health via Writing","score":0.17010000348091125,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.03830000013113022,"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":0.7688000202178955},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5813000202178955},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.4223000109195709},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.29649999737739563}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7688000202178955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056999802589417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6215000152587891},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5813000202178955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2012378416","https://openalex.org/W4285294723","https://openalex.org/W4309674289","https://openalex.org/W4389518784","https://openalex.org/W4389524379","https://openalex.org/W4392669753","https://openalex.org/W4402672022","https://openalex.org/W4404534210"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,73,82],"rapid":[2],"advancement":[3],"of":[4,84],"large":[5],"language":[6],"models,":[7],"they":[8],"remain":[9],"highly":[10],"susceptible":[11],"to":[12],"generating":[13],"hallucinations,":[14],"which":[15],"significantly":[16],"hinders":[17],"their":[18],"widespread":[19],"application.":[20],"Hallucination":[21],"research":[22],"requires":[23],"dynamic":[24],"and":[25,43,77,123],"fine-grained":[26,60],"evaluation.":[27],"However,":[28],"most":[29],"existing":[30],"hallucination":[31,45,95],"benchmarks":[32],"(especially":[33],"in":[34],"Chinese":[35,93],"language)":[36],"rely":[37],"on":[38,65],"human":[39],"annotations,":[40],"making":[41],"automatical":[42],"cost-effective":[44],"evaluation":[46],"challenging.":[47],"To":[48],"address":[49],"this,":[50],"we":[51,89],"introduce":[52],"HaluAgent,":[53,88],"an":[54],"agentic":[55],"framework":[56],"that":[57,72],"automatically":[58],"constructs":[59],"question-answering":[61],"(QA)":[62],"dataset":[63],"based":[64],"some":[66],"knowledge":[67,100],"documents.":[68],"Our":[69],"experiments":[70],"demonstrate":[71],"manually":[74],"designed":[75],"rules":[76],"prompt":[78],"optimization":[79],"can":[80],"improve":[81],"quality":[83],"generated":[85],"data.":[86],"Using":[87],"construct":[90],"C-FAITH,":[91,118],"a":[92],"QA":[94],"benchmark":[96],"created":[97],"from":[98,103],"1,399":[99],"documents":[101],"obtained":[102],"web":[104],"scraping,":[105],"totaling":[106],"60,702":[107],"entries.":[108],"We":[109],"comprehensively":[110],"evaluate":[111],"16":[112],"mainstream":[113],"LLMs":[114],"with":[115],"our":[116],"proposed":[117],"providing":[119],"detailed":[120],"experimental":[121],"results":[122],"analysis.":[124]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-08T00:00:00"}