{"id":"https://openalex.org/W4416251113","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227655","title":"Interventional Prompt-Tuning for Relation Extraction","display_name":"Interventional Prompt-Tuning for Relation Extraction","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251113","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227655"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100445235","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-5561-4435"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhonglin Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonglin Guo","raw_affiliation_strings":["Institute of Control and Electronic Technology,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Control and Electronic Technology,Beijing,China","institution_ids":["https://openalex.org/I202334528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050017370","display_name":"Liqiang Wen","orcid":"https://orcid.org/0000-0002-0278-8888"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Wen","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022637754","display_name":"Yipu Chen","orcid":"https://orcid.org/0000-0002-5079-4334"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yipu Chen","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422377","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8182-2852"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107006795","display_name":"Wen Zhao","orcid":"https://orcid.org/0009-0000-1523-5740"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Zhao","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16547579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9146999716758728,"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":0.9146999716758728,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.015399999916553497,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.011699999682605267,"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/relation","display_name":"Relation (database)","score":0.6261000037193298},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6237000226974487},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5781000256538391},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.532800018787384},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.4742000102996826},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/backdoor","display_name":"Backdoor","score":0.3937000036239624},{"id":"https://openalex.org/keywords/bivariate-analysis","display_name":"Bivariate analysis","score":0.36419999599456787},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6237000226974487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5917999744415283},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5781000256538391},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860000014305115},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C64341305","wikidata":"https://www.wikidata.org/wiki/Q4919225","display_name":"Bivariate analysis","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33629998564720154},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2988080768","wikidata":"https://www.wikidata.org/wiki/Q7095057","display_name":"Semantic relation","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2779658751","wikidata":"https://www.wikidata.org/wiki/Q581459","display_name":"Antipathy","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2049910836","https://openalex.org/W2143891888","https://openalex.org/W2759211898","https://openalex.org/W2962833164","https://openalex.org/W2963718112","https://openalex.org/W2964167098","https://openalex.org/W2984452801","https://openalex.org/W3034891697","https://openalex.org/W3098267758","https://openalex.org/W3104415840","https://openalex.org/W3112076981","https://openalex.org/W3153427360","https://openalex.org/W3164548985","https://openalex.org/W3166846774","https://openalex.org/W3173673636","https://openalex.org/W3176762756","https://openalex.org/W3194836374","https://openalex.org/W3198490223","https://openalex.org/W3198599617","https://openalex.org/W3207577858","https://openalex.org/W3212660220","https://openalex.org/W4280518705","https://openalex.org/W4285230133","https://openalex.org/W4285306609","https://openalex.org/W4309811444","https://openalex.org/W4312516176","https://openalex.org/W4389519918","https://openalex.org/W4404784155"],"related_works":[],"abstract_inverted_index":{"Prompt-Tuning":[0],"has":[1],"become":[2],"a":[3,49,58,89],"popular":[4],"paradigm":[5],"to":[6,61,72,111],"leverage":[7],"large-scale":[8],"pre-trained":[9,55],"language":[10],"models":[11],"(PLMs)":[12],"in":[13,27,115,141],"relation":[14,42,65,75],"extraction":[15],"(RE).":[16],"We":[17,44,69],"show":[18],"that":[19,53],"the":[20,54,116,134],"rich":[21],"prior":[22,138],"knowledge":[23,56,140],"of":[24,103,137],"relational":[25],"facts":[26],"PLMs,":[28],"while":[29],"improving":[30],"RE":[31,129],"performance,":[32],"may":[33],"have":[34],"unintended":[35],"harmful":[36],"effects":[37],"when":[38],"semantically":[39],"distant":[40],"from":[41,48],"descriptions.":[43],"investigate":[45],"this":[46],"phenomenon":[47],"causal":[50],"view,":[51],"revealing":[52],"is":[57,105],"confounder":[59],"leading":[60],"spurious":[62],"correlations":[63],"between":[64],"representations":[66,76],"and":[67,131],"labels.":[68],"thus":[70],"propose":[71],"intervene":[73],"on":[74,81,125],"via":[77],"backdoor":[78],"adjustment":[79],"conditioning":[80],"verbalizers,":[82],"attaining":[83],"an":[84,108],"interventional":[85],"prompt-tuning":[86],"method":[87,120],"with":[88,107],"multi-mask":[90],"orthogonality":[91],"regularization":[92],"mechanism.":[93],"Specifically,":[94],"we":[95],"exploit":[96],"multiple":[97],"mutually":[98],"orthogonal":[99],"mask":[100],"representations,":[101],"each":[102],"which":[104],"paired":[106],"individual":[109],"verbalizer,":[110],"approximate":[112],"verbalizer":[113],"sampling":[114],"intervention":[117],"implementation.":[118],"Our":[119],"impressively":[121],"achieves":[122],"competitive":[123],"performance":[124],"four":[126],"widely":[127],"used":[128],"datasets":[130],"significantly":[132],"alleviates":[133],"misleading":[135],"impacts":[136],"factual":[139],"PLMs.":[142]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}