{"id":"https://openalex.org/W7167932929","doi":"https://doi.org/10.1145/3805712.3808516","title":"Code-Based English Models Reveal Surprising Performance on Chinese QA Pair Extraction Task","display_name":"Code-Based English Models Reveal Surprising Performance on Chinese QA Pair Extraction Task","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167932929","doi":"https://doi.org/10.1145/3805712.3808516"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808516","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808516","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808516","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042375352","display_name":"Jiajun Yu","orcid":"https://orcid.org/0009-0007-9428-4938"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Yu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-9428-4938","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140403285","display_name":"Linghan Zheng","orcid":"https://orcid.org/0009-0008-8413-9726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linghan Zheng","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-8413-9726","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140418406","display_name":"Hui Liu","orcid":"https://orcid.org/0009-0000-0949-2150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-0949-2150","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140415021","display_name":"Jiayuan Dong","orcid":"https://orcid.org/0009-0004-5366-3702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayuan Dong","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-5366-3702","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140426612","display_name":"Yue Shen","orcid":"https://orcid.org/0009-0007-8876-9859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Shen","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-8876-9859","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001841701","display_name":"Zhiwei Liu","orcid":"https://orcid.org/0000-0002-4829-0751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwei Liu","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4829-0751","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140385029","display_name":"Yaozhen Liang","orcid":"https://orcid.org/0009-0000-5625-9204"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaozhen Liang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-5625-9204","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140440915","display_name":"Yong Li","orcid":"https://orcid.org/0009-0005-1664-6425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-1664-6425","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047118636","display_name":"Haishuai Wang","orcid":"https://orcid.org/0000-0003-1617-0920"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haishuai Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1617-0920","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"5060","last_page":"5066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7964000105857849,"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":0.7964000105857849,"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":0.05719999969005585,"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/T13629","display_name":"Text Readability and Simplification","score":0.022199999541044235,"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/task","display_name":"Task (project management)","score":0.6535000205039978},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6259999871253967},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48660001158714294},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41119998693466187},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.38359999656677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261999845504761},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6259999871253967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.597100019454956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4916999936103821},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41119998693466187},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2709999978542328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808516","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808516","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808516","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808516","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5959900617599487,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2962977247","https://openalex.org/W2963661590","https://openalex.org/W3003604522","https://openalex.org/W4389519118","https://openalex.org/W4389519863","https://openalex.org/W4402670318","https://openalex.org/W4407632367","https://openalex.org/W4412886849","https://openalex.org/W4412888873","https://openalex.org/W4413145922","https://openalex.org/W4414281281","https://openalex.org/W7131796490","https://openalex.org/W7137897857","https://openalex.org/W7140108883"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"advancements":[3],"in":[4,16,49,168],"automated":[5],"Question-Answer":[6],"(QA)":[7],"extraction":[8,57,137],"using":[9],"large":[10],"language":[11],"models":[12,66,78],"(LLMs),":[13],"addressing":[14],"challenges":[15],"transforming":[17],"unstructured":[18],"text":[19,81],"into":[20,112],"high-quality,":[21],"retrievable":[22],"QA":[23,56,136,150],"pairs.":[24],"Traditional":[25],"approaches,":[26],"whether":[27],"through":[28,154],"segmented":[29],"question":[30],"and":[31,43,62,69,160],"answer":[32],"generation":[33],"or":[34],"end-to-end":[35],"extraction,":[36],"often":[37],"struggle":[38],"with":[39,59,82,97],"efficiency,":[40],"dataset":[41,58],"limitations,":[42],"performance":[44],"consistency.":[45],"Leveraging":[46],"recent":[47],"progress":[48],"LLMs,":[50],"we":[51,91],"constructed":[52],"a":[53,83,133,169],"large-scale":[54],"Chinese":[55,80,100,135,149,158],"143,846":[60],"documents":[61],"evaluated":[63],"multiple":[64],"fine-tuned":[65,166],"on":[67,79],"public":[68],"private":[70],"datasets.":[71],"Surprisingly,":[72],"code-based":[73,95,146],"English":[74],"LLMs":[75,147],"outperformed":[76],"Chinese-specialized":[77],"lower":[84],"hallucination":[85],"rate.":[86],"Building":[87],"upon":[88],"this":[89],"finding,":[90],"enhanced":[92,153],"the":[93,165],"best-performing":[94],"model":[96],"an":[98],"expanded":[99,157],"vocabulary,":[101],"creating":[102],"Code":[103,110,155],"Llama-M,":[104],"which":[105],"achieved":[106],"better":[107],"results.":[108],"Integrating":[109],"Llama-M":[111],"our":[113],"internal":[114],"assistant,":[115],"Luo":[116],"Ying,":[117],"demonstrated":[118],"notable":[119],"user":[120,174],"satisfaction":[121],"gains,":[122],"affirming":[123],"its":[124],"practical":[125],"impact.":[126],"Key":[127],"contributions":[128],"include:":[129],"(i)":[130],"creation":[131],"of":[132,142,145,164],"robust":[134],"instruction":[138],"dataset;":[139],"(ii)":[140],"evidence":[141],"cross-lingual":[143],"efficacy":[144],"for":[148],"tasks,":[151],"further":[152],"Llama-M's":[156],"vocabulary;":[159],"(iii)":[161],"successful":[162],"application":[163],"LLM":[167],"live":[170],"assistant":[171],"system,":[172],"enhancing":[173],"experience.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}