{"id":"https://openalex.org/W7166799156","doi":"https://doi.org/10.18653/v1/2026.acl-long.1520","title":"Synthetic Data Generation for Training Diversified Commonsense Reasoning Models","display_name":"Synthetic Data Generation for Training Diversified Commonsense Reasoning Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166799156","doi":"https://doi.org/10.18653/v1/2026.acl-long.1520"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1520","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1520","pdf_url":"https://aclanthology.org/2026.acl-long.1520.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 64th 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/2026.acl-long.1520.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139761342","display_name":"Tianhui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianhui Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139754338","display_name":"Bei Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bei Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139794368","display_name":"Danushka Bollegala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danushka Bollegala","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78851474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32916","last_page":"32937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09000000357627869,"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":0.09000000357627869,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.08540000021457672,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.08290000259876251,"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/training","display_name":"Training (meteorology)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.39309999346733093},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.38339999318122864},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.3490000069141388},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2797999978065491},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2639999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.582099974155426},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1520","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1520","pdf_url":"https://aclanthology.org/2026.acl-long.1520.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1520","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1520","pdf_url":"https://aclanthology.org/2026.acl-long.1520.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166799156.pdf","grobid_xml":"https://content.openalex.org/works/W7166799156.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conversational":[0],"agents":[1],"are":[2,69],"required":[3],"to":[4,6,32,58,96],"respond":[5],"their":[7,27],"users":[8],"not":[9],"only":[10,79],"with":[11,122],"high":[12,60],"quality":[13,120],"(i.e.commonsense-bearing)":[14],"responses,":[15],"but":[16],"also":[17],"considering":[18],"multiple":[19],"plausible":[20],"alternative":[21],"scenarios,":[22],"reflecting":[23],"the":[24,29,37,49,59,99],"diversity":[25,118],"in":[26,115],"responses.Despite":[28],"growing":[30],"need":[31],"train":[33],"diverse":[34,54],"commonsense":[35,55,84],"generators,":[36],"progress":[38],"of":[39,42,51,75,83],"this":[40,87],"line":[41],"work":[43],"has":[44],"been":[45],"significantly":[46],"hindered":[47],"by":[48],"lack":[50],"large-scale":[52],"high-quality":[53],"training":[56,88],"datasets.Due":[57],"annotation":[61],"costs,":[62],"existing":[63],"Generative":[64],"Commonsense":[65],"Reasoning":[66],"(GCR)":[67],"datasets":[68],"created":[70],"using":[71],"a":[72,80,93],"small":[73],"number":[74],"human":[76],"annotators,":[77],"covering":[78],"narrow":[81],"set":[82],"scenarios.To":[85],"address":[86],"resource":[89],"gap,":[90],"we":[91],"propose":[92],"two-stage":[94],"method":[95],"create":[97],"CommonSyn,":[98],"first-ever":[100],"synthetic":[101],"dataset":[102],"for":[103],"diversified":[104],"GCR.Large":[105],"Language":[106],"Models":[107],"(LLMs)":[108],"fine-tuned":[109,127],"on":[110,128],"CommonSyn":[111],"show":[112],"simultaneous":[113],"improvements":[114],"both":[116],"generation":[117],"and":[119,125],"compared":[121],"vanilla":[123],"models":[124,126],"manually":[129],"annotated":[130],"datasets.":[131],"1":[132]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}