{"id":"https://openalex.org/W3031652686","doi":"https://doi.org/10.1162/coli_a_00404","title":"CausaLM: Causal Model Explanation Through Counterfactual Language Models","display_name":"CausaLM: Causal Model Explanation Through Counterfactual Language Models","publication_year":2021,"publication_date":"2021-03-29","ids":{"openalex":"https://openalex.org/W3031652686","doi":"https://doi.org/10.1162/coli_a_00404","mag":"3031652686"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00404","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00404","pdf_url":"https://direct.mit.edu/coli/article-pdf/47/2/333/1938107/coli_a_00404.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/47/2/333/1938107/coli_a_00404.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Amir Feder","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Amir Feder","raw_affiliation_strings":["Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. feder@campus.technion.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. feder@campus.technion.ac.il","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nadav Oved","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nadav Oved","raw_affiliation_strings":["Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. nadavo@campus.technion.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. nadavo@campus.technion.ac.il","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Uri Shalit","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Uri Shalit","raw_affiliation_strings":["Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. urishalit@technion.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. urishalit@technion.ac.il","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":null,"display_name":"Roi Reichart","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roi Reichart","raw_affiliation_strings":["Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. roiri@technion.ac.il"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Industrial Engineering and Management, Technion - Israel Institute of Technology. roiri@technion.ac.il","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":3.9176,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94426305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.675000011920929,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.675000011920929,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0731000006198883,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10028","display_name":"Topic Modeling","score":0.042100001126527786,"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":0.9355999827384949},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.7505000233650208},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6844000220298767},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6682999730110168},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5648000240325928},{"id":"https://openalex.org/keywords/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.51910001039505},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5040000081062317},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45910000801086426}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9355999827384949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646999955177307},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.7505000233650208},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6844000220298767},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6682999730110168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294000148773193},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5648000240325928},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.51910001039505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5081999897956848},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C79897977","wikidata":"https://www.wikidata.org/wiki/Q5054568","display_name":"Causal chain","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/coli_a_00404","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00404","pdf_url":"https://direct.mit.edu/coli/article-pdf/47/2/333/1938107/coli_a_00404.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2005.13407","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.13407","pdf_url":"https://arxiv.org/pdf/2005.13407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:695c189dcd6c464bb43626363309264e","is_oa":true,"landing_page_url":"https://doaj.org/article/695c189dcd6c464bb43626363309264e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 47, Iss 2, Pp 333-386 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00404","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00404","pdf_url":"https://direct.mit.edu/coli/article-pdf/47/2/333/1938107/coli_a_00404.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Understanding":[1],"predictions":[2],"made":[3],"by":[4,151,201],"deep":[5,131],"neural":[6],"networks":[7],"is":[8,88,99,126,193,199],"notoriously":[9],"difficult,":[10],"but":[11],"also":[12,32],"crucial":[13],"to":[14,179],"their":[15,27],"dissemination.":[16],"As":[17],"all":[18],"machine":[19],"learning\u2013based":[20],"methods,":[21],"they":[22,48],"are":[23,38],"as":[24,26,162],"good":[25],"training":[28],"data,":[29],"and":[30,54,56,63,176],"can":[31,41,164,206],"capture":[33],"unwanted":[34,211],"biases.":[35],"While":[36],"there":[37],"tools":[39],"that":[40,89,107,150,198],"help":[42],"understand":[43],"whether":[44],"such":[45,161],"biases":[46],"exist,":[47],"do":[49],"not":[50],"distinguish":[51],"between":[52],"correlation":[53],"causation,":[55],"might":[57],"be":[58,177,207],"ill-suited":[59],"for":[60,64,114,170],"text-based":[61],"models":[62,134,160],"reasoning":[65],"about":[66],"high":[67],"level":[68],"language":[69,121,158,195],"concepts.":[70],"A":[71,188],"key":[72],"problem":[73],"of":[74,79,82,95,130,144,174,190],"estimating":[75],"the":[76,93,141,145,202,215],"causal":[77,116,142,183],"effect":[78,184],"a":[80,85,112,167,171,194],"concept":[81,173],"interest":[83],"on":[84,128,185],"given":[86,172],"model":[87,117,186,197],"this":[90],"estimation":[91],"requires":[92],"generation":[94,103],"counterfactual":[96,120,168],"examples,":[97],"which":[98,205],"challenging":[100],"with":[101,135],"existing":[102],"technology.":[104],"To":[105],"bridge":[106],"gap,":[108],"we":[109,148],"propose":[110],"CausaLM,":[111],"framework":[113],"producing":[115],"explanations":[118],"using":[119],"representation":[122,159,169,196],"models.":[123],"Our":[124],"approach":[125],"based":[127],"fine-tuning":[129],"contextualized":[132],"embedding":[133],"auxiliary":[136,154],"adversarial":[137,155],"tasks":[138],"derived":[139],"from":[140],"graph":[143],"problem.":[146],"Concretely,":[147],"show":[149],"carefully":[152],"choosing":[153],"pre-training":[156],"tasks,":[157],"BERT":[163],"effectively":[165],"learn":[166],"interest,":[175],"used":[178],"estimate":[180],"its":[181],"true":[182],"performance.":[187],"byproduct":[189],"our":[191],"method":[192],"unaffected":[200],"tested":[203],"concept,":[204],"useful":[208],"in":[209,214],"mitigating":[210],"bias":[212],"ingrained":[213],"data.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2020-06-05T00:00:00"}