{"id":"https://openalex.org/W4412945707","doi":"https://doi.org/10.18653/v1/2025.acl-long.260","title":"Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model","display_name":"Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945707","doi":"https://doi.org/10.18653/v1/2025.acl-long.260"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.260","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.260","pdf_url":"https://aclanthology.org/2025.acl-long.260.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.260.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055755839","display_name":"Luhao Zhang","orcid":"https://orcid.org/0000-0001-5725-6830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luhao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390734","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0009-0006-4229-7318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063307425","display_name":"Linmei Hu","orcid":"https://orcid.org/0000-0003-0993-8495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linmei Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674656","display_name":"Dandan Song","orcid":"https://orcid.org/0000-0002-5050-8211"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dandan Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114040645","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqiang Nie","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5216","last_page":"5227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.5494999885559082,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12034","display_name":"Digital and Cyber Forensics","score":0.5494999885559082,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.5444999933242798,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8636581897735596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6262288689613342},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4421147108078003},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2472309172153473},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12079963088035583},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10463705658912659}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8636581897735596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6262288689613342},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4421147108078003},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2472309172153473},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12079963088035583},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10463705658912659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.260","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.260","pdf_url":"https://aclanthology.org/2025.acl-long.260.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.260","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.260","pdf_url":"https://aclanthology.org/2025.acl-long.260.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2815490039","display_name":null,"funder_award_id":"62276029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323110","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74"},{"id":"https://openalex.org/F4320327514","display_name":"Beijing Institute of Technology Research Fund Program for Young Scholars","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945707.pdf","grobid_xml":"https://content.openalex.org/works/W4412945707.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/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2390660599"],"abstract_inverted_index":{"Counterfactual":[0],"data":[1,55,88,148,161],"augmentation,":[2],"which":[3,115],"generates":[4],"minimally":[5],"edited":[6],"tokens":[7],"to":[8,16,38,109,134,151],"alter":[9],"labels,":[10],"has":[11,48],"become":[12],"a":[13,84,98,123,141],"key":[14],"approach":[15],"improving":[17,181],"model":[18,108,155],"robustness":[19],"in":[20,64,176],"natural":[21],"language":[22,45],"processing.It":[23],"is":[24,116,132,149],"usually":[25],"implemented":[26],"by":[27],"first":[28],"identifying":[29],"the":[30,51,68,74,80,93,102,106,111,120,153,157,170],"causal":[31,70,113],"terms":[32,37],"and":[33,72,118,162],"then":[34],"modifying":[35],"these":[36],"create":[39],"counterfactual":[40,54,87],"candidates.The":[41],"emergence":[42],"of":[43,53,76,105,159,172],"large":[44],"models":[46],"(LLMs)":[47],"effectively":[49],"facilitated":[50],"task":[52,107,154,182],"augmentation.However,":[56],"existing":[57,160],"LLMbased":[58],"approaches":[59],"still":[60],"face":[61],"some":[62],"challenges":[63],"1)":[65],"accurately":[66],"extracting":[67],"task-specific":[69,112],"terms,":[71,114],"2)":[73],"quality":[75],"LLM-generated":[77,136],"counterfacts.To":[78],"address":[79],"issues,":[81],"we":[82,96],"propose":[83],"dually":[85],"self-improved":[86,99,125],"augmentation":[89],"method":[90,175],"using":[91],"LLM.On":[92],"one":[94],"hand,":[95,122],"design":[97],"strategy":[100,126],"employing":[101],"attention":[103],"distribution":[104],"identify":[110],"lightweight":[117],"task-specific.On":[119],"other":[121],"second":[124],"based":[127],"on":[128,146,156,166],"direct":[129],"preference":[130],"optimization":[131],"utilized":[133],"refine":[135],"counterfacts,":[137],"achieving":[138],"high-quality":[139,178],"counterfacts.Finally,":[140],"balanced":[142],"loss":[143],"preventing":[144],"over-emphasis":[145],"augmentated":[147],"proposed":[150,174],"retrain":[152],"fusion":[158],"generated":[163],"counterfacts.Extensive":[164],"experiments":[165],"multiple":[167],"benchmarks":[168],"demonstrate":[169],"effectiveness":[171],"our":[173],"generating":[177],"counterfacts":[179],"for":[180],"performance.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}