{"id":"https://openalex.org/W7166827055","doi":"https://doi.org/10.18653/v1/2026.acl-long.782","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","display_name":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166827055","doi":"https://doi.org/10.18653/v1/2026.acl-long.782"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.782","pdf_url":"https://aclanthology.org/2026.acl-long.782.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.782.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139844625","display_name":"Aaron Mueller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aaron Mueller","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139772582","display_name":"Andrew Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Lee","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139794919","display_name":"Shruti Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shruti Joshi","raw_affiliation_strings":["Mila -Quebec AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila -Quebec AI Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139835645","display_name":"Ekdeep Singh Lubana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122854","display_name":"Sunfire (Germany)","ror":"https://ror.org/02pfxyr52","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210122854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ekdeep Singh Lubana","raw_affiliation_strings":["Goodfire"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Goodfire","institution_ids":["https://openalex.org/I4210122854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109398524","display_name":"Dhanya Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dhanya Sridhar","raw_affiliation_strings":["Mila -Quebec AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila -Quebec AI Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034660028","display_name":"Patrik Reizinger","orcid":"https://orcid.org/0000-0001-9861-0293"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrik Reizinger","raw_affiliation_strings":["University of T\u00fcbingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.79436965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17188","last_page":"17210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.529699981212616,"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":0.529699981212616,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.030899999663233757,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.03020000085234642,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8790000081062317},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.3714999854564667},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3700999915599823},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8790000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705999732017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5238999724388123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.782","pdf_url":"https://aclanthology.org/2026.acl-long.782.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.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.782","pdf_url":"https://aclanthology.org/2026.acl-long.782.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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5424578189849854}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310638","display_name":"McGill University","ror":"https://ror.org/01pxwe438"},{"id":"https://openalex.org/F4320317967","display_name":"International Max Planck Research School for Environmental, Cellular and Molecular Microbiology","ror":null},{"id":"https://openalex.org/F4320327553","display_name":"International Max Planck Research School for Advanced Methods in Process and Systems Engineering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166827055.pdf","grobid_xml":"https://content.openalex.org/works/W7166827055.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Aaron":[0],"Mueller,":[1],"Andrew":[2],"Lee,":[3],"Shruti":[4],"Joshi,":[5],"Ekdeep":[6],"Singh":[7],"Lubana,":[8],"Dhanya":[9],"Sridhar,":[10],"Patrik":[11],"Reizinger.":[12],"Proceedings":[13],"of":[14,19],"the":[15,20],"64th":[16],"Annual":[17],"Meeting":[18],"Association":[21],"for":[22],"Computational":[23],"Linguistics":[24],"(Volume":[25],"1:":[26],"Long":[27],"Papers).":[28],"2026.":[29]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}
