{"id":"https://openalex.org/W4412346863","doi":"https://doi.org/10.1109/kse63888.2024.11063523","title":"Enhancing Reading Comprehension of Vietnamese LLMs with Synthetic Data","display_name":"Enhancing Reading Comprehension of Vietnamese LLMs with Synthetic Data","publication_year":2024,"publication_date":"2024-11-05","ids":{"openalex":"https://openalex.org/W4412346863","doi":"https://doi.org/10.1109/kse63888.2024.11063523"},"language":"en","primary_location":{"id":"doi:10.1109/kse63888.2024.11063523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse63888.2024.11063523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 16th International Conference on Knowledge and System Engineering (KSE)","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/A5045945635","display_name":"Thang M. Le","orcid":"https://orcid.org/0000-0002-4196-8646"},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Thang V.Q. Le","raw_affiliation_strings":["Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107446421","display_name":"Nguyen Nguyen","orcid":"https://orcid.org/0000-0003-1553-3224"},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen P. Nguyen","raw_affiliation_strings":["Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012007387","display_name":"Thi Thuy Duong","orcid":"https://orcid.org/0000-0003-1796-3850"},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Trong-Chi Duong","raw_affiliation_strings":["Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067682200","display_name":"Anh-Cuong Le","orcid":"https://orcid.org/0000-0003-2645-1419"},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Anh-Cuong Le","raw_affiliation_strings":["Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University,Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006414955","display_name":"Viet-Cuong Nguyen","orcid":"https://orcid.org/0000-0002-8008-582X"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["GB","VN"],"is_corresponding":false,"raw_author_name":"Viet-Cuong Nguyen","raw_affiliation_strings":["Institute for Artificial Intelligence, VNU University of Engineering and Technology,Hanoi,Vietnam","Intelligent Integration Co. Ltd (INT2),Vietnam"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, VNU University of Engineering and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I67868205"]},{"raw_affiliation_string":"Intelligent Integration Co. Ltd (INT2),Vietnam","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028586199","display_name":"Viet-Ha Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["GB","VN"],"is_corresponding":false,"raw_author_name":"Viet-Ha Nguyen","raw_affiliation_strings":["Institute for Artificial Intelligence, VNU University of Engineering and Technology,Hanoi,Vietnam","Intelligent Integration Co. Ltd (INT2),Vietnam"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, VNU University of Engineering and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I67868205"]},{"raw_affiliation_string":"Intelligent Integration Co. Ltd (INT2),Vietnam","institution_ids":["https://openalex.org/I4210153682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045945635"],"corresponding_institution_ids":["https://openalex.org/I141445968"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28446496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"327","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9941999912261963,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9941999912261963,"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":0.9871000051498413,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/vietnamese","display_name":"Vietnamese","score":0.8046469688415527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5760557651519775},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5304391384124756},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.42647063732147217},{"id":"https://openalex.org/keywords/reading-comprehension","display_name":"Reading comprehension","score":0.41876447200775146},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.247919499874115},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14937886595726013}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8046469688415527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5760557651519775},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5304391384124756},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.42647063732147217},{"id":"https://openalex.org/C2778780117","wikidata":"https://www.wikidata.org/wiki/Q3269423","display_name":"Reading comprehension","level":3,"score":0.41876447200775146},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.247919499874115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14937886595726013},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kse63888.2024.11063523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kse63888.2024.11063523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 16th International Conference on Knowledge and System Engineering (KSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8899999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W3100452049","https://openalex.org/W4381855801","https://openalex.org/W4386507404","https://openalex.org/W4402671731","https://openalex.org/W4404782759","https://openalex.org/W6755207826","https://openalex.org/W6772383348","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6809646742","https://openalex.org/W6846915134","https://openalex.org/W6852232343","https://openalex.org/W6853444283","https://openalex.org/W6856274733","https://openalex.org/W6856663697","https://openalex.org/W6856880082","https://openalex.org/W6862405158","https://openalex.org/W6864527560","https://openalex.org/W6866860863"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2901286616","https://openalex.org/W2291461084","https://openalex.org/W2050882094","https://openalex.org/W2082296339","https://openalex.org/W2161828220","https://openalex.org/W1972348076","https://openalex.org/W2083863157"],"abstract_inverted_index":{"Large":[0],"Language":[1,93],"Models":[2,94],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7,149],"in":[8,28,38,102,120,146],"addressing":[9],"a":[10,19,62,125],"wide":[11],"array":[12],"of":[13,22,41,60,85,110,127,172],"general":[14],"problems.":[15],"However,":[16],"there":[17],"is":[18],"growing":[20],"recognition":[21],"the":[23,39,58,69,83,103,147,151,170],"need":[24],"for":[25,68,96],"domain-specific":[26,174],"expertise":[27],"certain":[29],"fields.":[30],"This":[31],"has":[32],"led":[33],"to":[34,46,78,156],"an":[35],"emerging":[36],"trend":[37],"development":[40,59],"specialized":[42],"LLMs,":[43],"often":[44],"referred":[45],"as":[47],"expert":[48],"models.":[49,158],"In":[50],"line":[51],"with":[52,117],"this":[53],"trend,":[54],"our":[55,173],"research":[56],"presents":[57],"Vilaw,":[61],"small":[63],"language":[64],"model":[65,80,161],"specifically":[66],"designed":[67],"Vietnamese":[70,152],"legal":[71,86,104,118,137,153,164],"domain.":[72,105],"Our":[73,159],"approach":[74],"combines":[75],"innovative":[76],"techniques":[77],"enhance":[79],"performance,":[81],"including":[82],"use":[84],"synthetic":[87,111],"data":[88,112,119],"and":[89,99,123,134,166],"experiments":[90],"on":[91],"Small":[92],"(SLMs)":[95],"continuing":[97],"pre-training":[98,121],"supervised":[100],"fine-tuning":[101],"We":[106],"created":[107],"new":[108],"types":[109],"by":[113],"adding":[114],"question-answering":[115,139],"generated":[116],"phase":[122],"developed":[124],"three-level":[126],"Bloom's":[128],"taxonomy":[129],"SFT":[130],"dataset:":[131],"knowledge,":[132],"comprehension":[133],"application,":[135,168],"especially":[136],"syllogism":[138],"data.":[140],"The":[141],"results":[142],"demonstrate":[143],"significant":[144],"improvements":[145],"model's":[148],"within":[150],"context":[154],"compared":[155],"baseline":[157],"Vilaw":[160],"exhibit":[162],"enhanced":[163],"reasoning":[165],"knowledge":[167],"showcasing":[169],"effectiveness":[171],"training":[175],"approach.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
