{"id":"https://openalex.org/W4412888388","doi":"https://doi.org/10.18653/v1/2025.findings-acl.439","title":"CDS: Data Synthesis Method Guided by Cognitive Diagnosis Theory","display_name":"CDS: Data Synthesis Method Guided by Cognitive Diagnosis Theory","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888388","doi":"https://doi.org/10.18653/v1/2025.findings-acl.439"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.439","pdf_url":"https://aclanthology.org/2025.findings-acl.439.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.439.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111174926","display_name":"Haokun Zhao","orcid":"https://orcid.org/0009-0006-5069-8840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haokun Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jinyi Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyi Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075507821","display_name":"Jiaqing Liang","orcid":"https://orcid.org/0000-0003-0670-5602"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqing Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanghua Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023448624","display_name":"Xiaojun Meng","orcid":"https://orcid.org/0000-0003-2425-7217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojun Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jiansheng Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiansheng Wei","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8370","last_page":"8393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.2824999988079071,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.2824999988079071,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6364960670471191},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.46386852860450745},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15616607666015625},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.11318841576576233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6364960670471191},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.46386852860450745},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15616607666015625},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.11318841576576233}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.439","pdf_url":"https://aclanthology.org/2025.findings-acl.439.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.439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.439","pdf_url":"https://aclanthology.org/2025.findings-acl.439.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888388.pdf","grobid_xml":"https://content.openalex.org/works/W4412888388.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"significant":[6,126],"advancements,":[7],"but":[8],"the":[9,19,60,86,113],"increasing":[10],"complexity":[11],"of":[12,48,117],"tasks":[13],"and":[14,81,108,115,143,148],"higher":[15],"performance":[16],"demands":[17],"highlight":[18],"need":[20],"for":[21,53,98],"continuous":[22],"improvement.Some":[23],"approaches":[24],"utilize":[25],"synthetic":[26],"data":[27,54,100,106,149],"generated":[28],"by":[29,72],"advanced":[30],"LLMs":[31],"based":[32],"on":[33,90,152],"evaluation":[34,40,79],"results":[35,80],"to":[36,43,77,111,133],"train":[37],"models.However,":[38],"conventional":[39],"methods":[41],"fail":[42],"provide":[44],"detailed,":[45],"fine-grained":[46],"profiles":[47,84],"LLMs,":[49],"limiting":[50],"their":[51],"guidance":[52],"synthesis.In":[55],"this":[56],"paper,":[57],"we":[58,93,102],"introduce":[59],"Cognitive":[61,73],"Diagnostic":[62],"Synthesis":[63],"(CDS)":[64],"method,":[65],"which":[66],"incorporates":[67],"a":[68],"diagnostic":[69],"process":[70],"inspired":[71],"Diagnosis":[74],"Theory":[75],"(CDT)":[76],"refine":[78],"characterize":[82],"model":[83],"at":[85],"knowledge":[87],"component":[88],"level.Based":[89],"these":[91],"diagnostics,":[92],"propose":[94],"two":[95],"diagnosis-synthesis":[96],"strategies":[97],"weakness-targeted":[99],"synthesis.Additionally,":[101],"present":[103],"an":[104],"enhanced":[105],"augmentation":[107],"selection":[109],"pipeline":[110],"improve":[112],"quality":[114],"diversity":[116],"synthesized":[118],"data.Our":[119],"experiments":[120],"with":[121],"several":[122],"open-source":[123],"models":[124],"show":[125],"improvements":[127],"across":[128],"multiple":[129],"benchmarks,":[130],"achieving":[131],"up":[132],"6.00%":[134],"improvement":[135],"in":[136,140,145],"code":[137],"generation,":[138],"13.10%":[139],"mathematical":[141],"reasoning,":[142],"5.43%":[144],"academic":[146],"exams.Code":[147],"are":[150],"available":[151],"GitHub":[153],"1":[154],".":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}