{"id":"https://openalex.org/W4412887996","doi":"https://doi.org/10.18653/v1/2025.findings-acl.748","title":"KnowCoder-X: Boosting Multilingual Information Extraction via Code","display_name":"KnowCoder-X: Boosting Multilingual Information Extraction via Code","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887996","doi":"https://doi.org/10.18653/v1/2025.findings-acl.748"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.748","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.748","pdf_url":"https://aclanthology.org/2025.findings-acl.748.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.748.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113051745","display_name":"Yuxin Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxin Zuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665456","display_name":"Wenxuan Jiang","orcid":"https://orcid.org/0000-0003-4690-899X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564554","display_name":"Wenxuan Liu","orcid":"https://orcid.org/0000-0002-1528-4224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674838","display_name":"Zixuan Li","orcid":"https://orcid.org/0009-0005-4713-3032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434323","display_name":"Long Bai","orcid":"https://orcid.org/0000-0003-2671-3298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038231583","display_name":"Hanbin Wang","orcid":"https://orcid.org/0000-0001-6927-2934"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanbin Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003892271","display_name":"Yutao Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutao Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102843658","display_name":"Xiaolong Jin","orcid":"https://orcid.org/0000-0003-3244-3941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036544715","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0009-0009-3990-4414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","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":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14486","last_page":"14509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9541000127792358,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9541000127792358,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9430999755859375,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9369000196456909,"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/boosting","display_name":"Boosting (machine learning)","score":0.9181457757949829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7546016573905945},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5540791153907776},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.519069254398346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.51448655128479},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4390214681625366},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42332300543785095},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27289360761642456}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.9181457757949829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7546016573905945},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5540791153907776},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.519069254398346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51448655128479},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4390214681625366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42332300543785095},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27289360761642456},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.748","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.748","pdf_url":"https://aclanthology.org/2025.findings-acl.748.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.748","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.748","pdf_url":"https://aclanthology.org/2025.findings-acl.748.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1943573793","display_name":null,"funder_award_id":"62306299","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887996.pdf","grobid_xml":"https://content.openalex.org/works/W4412887996.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2368651715"],"abstract_inverted_index":{"Empirical":[0],"evidence":[1],"indicates":[2],"that":[3,159],"LLMs":[4,10],"exhibit":[5],"spontaneous":[6],"cross-lingual":[7,13,40,78],"alignment.However,":[8],"although":[9],"show":[11],"promising":[12],"alignment":[14,79],"in":[15,127,151],"Information":[16],"Extraction":[17],"(IE),":[18],"a":[19,34,58,70,99],"significant":[20],"imbalance":[21],"across":[22,61,65],"languages":[23,66],"persists,":[24],"highlighting":[25],"an":[26],"underlying":[27],"deficiency.To":[28],"address":[29],"this,":[30],"we":[31,75,96],"propose":[32],"KnowCoder-X,":[33],"powerful":[35],"code":[36,72,171],"LLM":[37],"with":[38,107,119],"advanced":[39],"and":[41,101,136,153,172],"multilingual":[42,52],"capabilities":[43],"for":[44],"universal":[45],"IE.Firstly,":[46],"it":[47],"standardizes":[48],"the":[49,83,90,168],"representation":[50],"of":[51],"schemas":[53],"using":[54],"Python":[55],"classes,":[56],"ensuring":[57],"consistent":[59],"ontology":[60],"different":[62],"languages.Then,":[63],"IE":[64,77,104,144,149,164,169],"is":[67],"formulated":[68],"as":[69],"unified":[71],"generation":[73],"task.Secondly,":[74],"conduct":[76],"instruction":[80],"tuning":[81],"on":[82,147],"translated":[84],"instance":[85],"prediction":[86],"task":[87],"to":[88,122],"enhance":[89],"model's":[91],"crosslingual":[92,143,163],"transferability.During":[93],"this":[94],"phase,":[95],"also":[97],"construct":[98],"high-quality":[100],"diverse":[102],"bilingual":[103],"parallel":[105],"dataset":[106,173],"257k":[108],"samples,":[109],"called":[110],"ParallelNER,":[111],"synthesized":[112],"by":[113,134,138],"our":[114],"proposed":[115],"robust":[116],"three-stage":[117],"pipeline,":[118],"manual":[120],"annotation":[121],"ensure":[123],"quality.Although":[124],"without":[125],"training":[126],"29":[128],"unseen":[129],"languages,":[130],"KnowCoder-X":[131,160],"surpasses":[132],"ChatGPT":[133],"30.17%":[135],"SoTA":[137],"20.03%,":[139],"thereby":[140],"demonstrating":[141],"superior":[142],"capabilities.Comprehensive":[145],"evaluations":[146],"64":[148],"benchmarks":[150],"Chinese":[152],"English":[154],"under":[155],"various":[156],"settings":[157],"demonstrate":[158],"significantly":[161],"enhances":[162],"transfer":[165],"through":[166],"boosting":[167],"alignment.Our":[170],"are":[174],"available":[175],"at:":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}