{"id":"https://openalex.org/W7140089725","doi":"https://doi.org/10.18653/v1/2026.eacl-long.139","title":"Safe-Unsafe Concept Separation Emerges from a Single Direction in Language Models Activation Space","display_name":"Safe-Unsafe Concept Separation Emerges from a Single Direction in Language Models Activation Space","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140089725","doi":"https://doi.org/10.18653/v1/2026.eacl-long.139"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.139","pdf_url":"https://aclanthology.org/2026.eacl-long.139.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.139.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116730227","display_name":"Andrea Ermellino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Ermellino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046882068","display_name":"Lorenzo Malandri","orcid":"https://orcid.org/0000-0002-0222-9365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Malandri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047827615","display_name":"Fabio Mercorio","orcid":"https://orcid.org/0000-0001-6864-2702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabio Mercorio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5099566317","display_name":"Antonio Serino","orcid":"https://orcid.org/0009-0008-0737-8547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Serino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"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":0.39375882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3019","last_page":"3034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3057999908924103,"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":0.3057999908924103,"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":0.14800000190734863,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.09369999915361404,"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/space","display_name":"Space (punctuation)","score":0.5059000253677368},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4787999987602234},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.32019999623298645},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.25200000405311584}],"concepts":[{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46720001101493835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33899998664855957},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.29350000619888306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2459000051021576}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.139","pdf_url":"https://aclanthology.org/2026.eacl-long.139.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.139","pdf_url":"https://aclanthology.org/2026.eacl-long.139.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5849632620811462,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140089725.pdf","grobid_xml":"https://content.openalex.org/works/W7140089725.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Andrea":[0],"Ermellino,":[1],"Lorenzo":[2],"Malandri,":[3],"Fabio":[4],"Mercorio,":[5],"Antonio":[6],"Serino.":[7],"Proceedings":[8],"of":[9,13,17],"the":[10,14,18],"19th":[11],"Conference":[12],"European":[15],"Chapter":[16],"Association":[19],"for":[20],"Computational":[21],"Linguistics":[22],"(Volume":[23],"1:":[24],"Long":[25],"Papers).":[26],"2026.":[27]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}
