{"id":"https://openalex.org/W7225192802","doi":"https://doi.org/10.1007/978-3-032-44176-8_39","title":"Embedding Quality for Safety Classification: A Systematic Benchmark of Guard Models, Base Decoders, and Encoders","display_name":"Embedding Quality for Safety Classification: A Systematic Benchmark of Guard Models, Base Decoders, and Encoders","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225192802","doi":"https://doi.org/10.1007/978-3-032-44176-8_39"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-44176-8_39","doi":"https://doi.org/10.1007/978-3-032-44176-8_39","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-44176-8_39","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7225175334","display_name":"Advances in Soft Computing"},"type":"conference-paper","is_traditional":true,"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/A5160438670","display_name":"Jose Ochoa-Sanchez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I113686770","display_name":"Instituto Tecnol\u00f3gico y de Estudios Superiores de Occidente","ror":"https://ror.org/00cwp6m07","country_code":"MX","type":"education","lineage":["https://openalex.org/I113686770"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Jose Ochoa-Sanchez","raw_affiliation_strings":["ITESO, Tlaquepaque, Jalisco, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITESO, Tlaquepaque, Jalisco, Mexico","institution_ids":["https://openalex.org/I113686770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072421430","display_name":"Roc\u00edo Carrasco-Navarro","orcid":"https://orcid.org/0000-0002-8148-3600","observed_orcids":["https://orcid.org/0000-0002-8148-3600"]},"institutions":[{"id":"https://openalex.org/I113686770","display_name":"Instituto Tecnol\u00f3gico y de Estudios Superiores de Occidente","ror":"https://ror.org/00cwp6m07","country_code":"MX","type":"education","lineage":["https://openalex.org/I113686770"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Rocio Carrasco-Navarro","raw_affiliation_strings":["ITESO, Tlaquepaque, Jalisco, Mexico"],"raw_orcid":"https://orcid.org/0000-0002-8148-3600","affiliations":[{"raw_affiliation_string":"ITESO, Tlaquepaque, Jalisco, Mexico","institution_ids":["https://openalex.org/I113686770"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020419869","display_name":"Ivan Reyes-Amezcua","orcid":"https://orcid.org/0000-0003-0120-3339","observed_orcids":["https://orcid.org/0000-0003-0120-3339"]},"institutions":[{"id":"https://openalex.org/I113686770","display_name":"Instituto Tecnol\u00f3gico y de Estudios Superiores de Occidente","ror":"https://ror.org/00cwp6m07","country_code":"MX","type":"education","lineage":["https://openalex.org/I113686770"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ivan Reyes-Amezcua","raw_affiliation_strings":["ITESO, Tlaquepaque, Jalisco, Mexico"],"raw_orcid":"https://orcid.org/0000-0003-0120-3339","affiliations":[{"raw_affiliation_string":"ITESO, Tlaquepaque, Jalisco, Mexico","institution_ids":["https://openalex.org/I113686770"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5160438670"],"corresponding_institution_ids":["https://openalex.org/I113686770"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"673","last_page":"691"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9692000150680542,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9692000150680542,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.014499999582767487,"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/T10028","display_name":"Topic Modeling","score":0.014100000262260437,"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/contextualized-embeddings","display_name":"contextual embeddings","score":0.6690000295639038},{"id":"https://openalex.org/keywords/safety-classification","display_name":"safety classification","score":0.5709999799728394},{"id":"https://openalex.org/keywords/hate-speech-detection","display_name":"hate speech detection","score":0.8870000243186951},{"id":"https://openalex.org/keywords/prompt-injection","display_name":"prompt injection","score":0.9810000061988831},{"id":"https://openalex.org/keywords/jailbreaking","display_name":"jailbreaking","score":0.9049999713897705},{"id":"https://openalex.org/keywords/stereotype-bias","display_name":"stereotype bias","score":0.9890000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8709999918937683},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C141141315","wikidata":"https://www.wikidata.org/wiki/Q2379942","display_name":"Guard (computer science)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34119999408721924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C6295992","wikidata":"https://www.wikidata.org/wiki/Q976521","display_name":"Cryptosystem","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-44176-8_39","doi":"https://doi.org/10.1007/978-3-032-44176-8_39","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-44176-8_39","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2144211451","https://openalex.org/W2882319491","https://openalex.org/W2922580172","https://openalex.org/W2954226438","https://openalex.org/W2963341956","https://openalex.org/W2970641574","https://openalex.org/W2983040767","https://openalex.org/W3019416653","https://openalex.org/W3101045333","https://openalex.org/W3154085251","https://openalex.org/W3211939470","https://openalex.org/W4225576545","https://openalex.org/W4389713766","https://openalex.org/W4393382253","https://openalex.org/W4394709004","https://openalex.org/W4401306886","https://openalex.org/W4402683079","https://openalex.org/W4403247651","https://openalex.org/W4404342689","https://openalex.org/W4404649539","https://openalex.org/W4404781557","https://openalex.org/W4404783313","https://openalex.org/W4405034402","https://openalex.org/W4405562150","https://openalex.org/W4405876080","https://openalex.org/W4407012266","https://openalex.org/W4414566258","https://openalex.org/W4414939355","https://openalex.org/W4415101693","https://openalex.org/W4415799204","https://openalex.org/W4417088133","https://openalex.org/W4417255468","https://openalex.org/W4417449953","https://openalex.org/W7092296780","https://openalex.org/W7140214824","https://openalex.org/W7166801299"],"related_works":["https://openalex.org/W7160877427","https://openalex.org/W7162795967","https://openalex.org/W7214788767","https://openalex.org/W7166821409","https://openalex.org/W4401306838","https://openalex.org/W7158627602","https://openalex.org/W4405876080","https://openalex.org/W7162814911","https://openalex.org/W7160425170","https://openalex.org/W7092296780"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}
