{"id":"https://openalex.org/W4415271252","doi":"https://doi.org/10.1007/s10462-025-11389-2","title":"Safeguarding large language models: a survey","display_name":"Safeguarding large language models: a survey","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415271252","doi":"https://doi.org/10.1007/s10462-025-11389-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/41114380"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-025-11389-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11389-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11389-2.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11389-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082505578","display_name":"Yi Dong","orcid":"https://orcid.org/0000-0001-9898-9571"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi Dong","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054272337","display_name":"Ronghui Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ronghui Mu","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081956313","display_name":"Yanghao Zhang","orcid":"https://orcid.org/0000-0002-8499-0974"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yanghao Zhang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102815325","display_name":"Siqi Sun","orcid":"https://orcid.org/0000-0002-9592-3670"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siqi Sun","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074422885","display_name":"Tianle Zhang","orcid":"https://orcid.org/0000-0002-0779-5905"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tianle Zhang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113190718","display_name":"Changshun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210113150","display_name":"Laboratoire Interdisciplinaire de Physique","ror":"https://ror.org/023n9q531","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Changshun Wu","raw_affiliation_strings":["IMAG, Universit\u00e9 Grenoble Alpes, Saint-Martin-d'H\u00e8res, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMAG, Universit\u00e9 Grenoble Alpes, Saint-Martin-d'H\u00e8res, France","institution_ids":["https://openalex.org/I36085230","https://openalex.org/I4210113150","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048979254","display_name":"Gaojie Jin","orcid":"https://orcid.org/0000-0003-0240-3033"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gaojie Jin","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102683796","display_name":"Yi Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi Qi","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102372527","display_name":"Jinwei Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinwei Hu","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100941260","display_name":"Jie Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Meng","raw_affiliation_strings":["Loughborough University, Loughborough, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106468718","display_name":"Saddek Bensalem","orcid":"https://orcid.org/0000-0002-5753-2126"},"institutions":[{"id":"https://openalex.org/I123791789","display_name":"Saint-Gobain (France)","ror":"https://ror.org/02fdb8q57","country_code":"FR","type":"company","lineage":["https://openalex.org/I123791789"]},{"id":"https://openalex.org/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210113150","display_name":"Laboratoire Interdisciplinaire de Physique","ror":"https://ror.org/023n9q531","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210113150","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Saddek Bensalem","raw_affiliation_strings":["CSX-AI, Saint-Didier-au-Mont-d'Or, France","IMAG, Universit\u00e9 Grenoble Alpes, Saint-Martin-d'H\u00e8res, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSX-AI, Saint-Didier-au-Mont-d'Or, France","institution_ids":["https://openalex.org/I123791789"]},{"raw_affiliation_string":"IMAG, Universit\u00e9 Grenoble Alpes, Saint-Martin-d'H\u00e8res, France","institution_ids":["https://openalex.org/I36085230","https://openalex.org/I4210113150","https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020085889","display_name":"Xiaowei Huang","orcid":"https://orcid.org/0000-0001-6267-0366"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Xiaowei Huang","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX UK","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Brownlow Street, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020085889"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":68.2797,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99927188,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"58","issue":"12","first_page":"382","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9976000189781189,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9879999756813049,"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":0.9866999983787537,"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/safeguarding","display_name":"Safeguarding","score":0.9602000117301941},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5060999989509583},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4180000126361847},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3977999985218048},{"id":"https://openalex.org/keywords/service-provider","display_name":"Service provider","score":0.37549999356269836},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.30820000171661377}],"concepts":[{"id":"https://openalex.org/C2776743756","wikidata":"https://www.wikidata.org/wiki/Q5097921","display_name":"Safeguarding","level":2,"score":0.9602000117301941},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.5879999995231628},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49399998784065247},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.37549999356269836},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2906000018119812},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C2986663376","wikidata":"https://www.wikidata.org/wiki/Q9465","display_name":"Ethical issues","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.26159998774528503},{"id":"https://openalex.org/C166735990","wikidata":"https://www.wikidata.org/wiki/Q1750812","display_name":"Human factors and ergonomics","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25279998779296875},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10462-025-11389-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11389-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11389-2.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},{"id":"pmid:41114380","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41114380","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial intelligence review","raw_type":null},{"id":"pmh:oai:europepmc.org:11340577","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12532640","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12532640/pdf/10462_2025_Article_11389.pdf","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s10462-025-11389-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11389-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11389-2.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6661291015","display_name":"EnnCore: End-to-End Conceptual Guarding of Neural Architectures","funder_award_id":"EP/T026995/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415271252.pdf"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W1969900674","https://openalex.org/W2038333915","https://openalex.org/W2108598243","https://openalex.org/W2171627300","https://openalex.org/W2473418344","https://openalex.org/W2535351973","https://openalex.org/W2773888539","https://openalex.org/W2946363484","https://openalex.org/W2947681066","https://openalex.org/W2962977603","https://openalex.org/W2963341956","https://openalex.org/W2971173235","https://openalex.org/W3021254583","https://openalex.org/W3034937117","https://openalex.org/W3034951181","https://openalex.org/W3037831233","https://openalex.org/W3095789240","https://openalex.org/W3100258764","https://openalex.org/W3100355250","https://openalex.org/W3102914525","https://openalex.org/W3104224589","https://openalex.org/W3134678353","https://openalex.org/W3153193605","https://openalex.org/W3155807546","https://openalex.org/W3158360872","https://openalex.org/W3168251909","https://openalex.org/W3203106571","https://openalex.org/W3204619801","https://openalex.org/W4205725534","https://openalex.org/W4206637810","https://openalex.org/W4221045317","https://openalex.org/W4225858632","https://openalex.org/W4226040778","https://openalex.org/W4283206275","https://openalex.org/W4309618884","https://openalex.org/W4365794479","https://openalex.org/W4367185264","https://openalex.org/W4367188881","https://openalex.org/W4383711355","https://openalex.org/W4385571122","https://openalex.org/W4385571225","https://openalex.org/W4385571495","https://openalex.org/W4385571830","https://openalex.org/W4385572039","https://openalex.org/W4385573200","https://openalex.org/W4385573323","https://openalex.org/W4385573539","https://openalex.org/W4385573644","https://openalex.org/W4385573783","https://openalex.org/W4385573981","https://openalex.org/W4385764073","https://openalex.org/W4385852384","https://openalex.org/W4385894687","https://openalex.org/W4386576626","https://openalex.org/W4387143023","https://openalex.org/W4388757737","https://openalex.org/W4388850876","https://openalex.org/W4388886073","https://openalex.org/W4389519367","https://openalex.org/W4389519598","https://openalex.org/W4389520749","https://openalex.org/W4389523771","https://openalex.org/W4389524162","https://openalex.org/W4389524506","https://openalex.org/W4389617257","https://openalex.org/W4390189975","https://openalex.org/W4390578204","https://openalex.org/W4391092855","https://openalex.org/W4391107732","https://openalex.org/W4392201111","https://openalex.org/W4393035858","https://openalex.org/W4393867901","https://openalex.org/W4396700714","https://openalex.org/W4396833426","https://openalex.org/W4399750638","https://openalex.org/W4400315206","https://openalex.org/W4400577092","https://openalex.org/W4401042286","https://openalex.org/W4401042550","https://openalex.org/W4401042900","https://openalex.org/W4401043228","https://openalex.org/W4401615053","https://openalex.org/W4402264157","https://openalex.org/W4402304442","https://openalex.org/W4402671666","https://openalex.org/W4402671718","https://openalex.org/W4404725774","https://openalex.org/W4404781959","https://openalex.org/W4404782219","https://openalex.org/W4404782283","https://openalex.org/W4405181291","https://openalex.org/W4405181600","https://openalex.org/W4406263753","https://openalex.org/W4408734515","https://openalex.org/W4409361739","https://openalex.org/W4414333247"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,25,41,71,74,86,94,133,138,141,146,150,166,180],"burgeoning":[2],"field":[3],"of":[4,28,44,77,183],"Large":[5],"Language":[6],"Models":[7],"(LLMs),":[8],"developing":[9],"a":[10,36,60,105,176],"robust":[11],"safety":[12],"mechanism,":[13],"colloquially":[14],"known":[15],"as":[16,112],"\"safeguards\"":[17],"or":[18],"\"guardrails\",":[19],"has":[20],"become":[21],"imperative":[22],"to":[23,96,109,125,131,136,174],"ensure":[24],"ethical":[26,65],"use":[27],"LLMs":[29],"within":[30],"prescribed":[31],"boundaries.":[32],"This":[33,90],"article":[34],"provides":[35],"systematic":[37],"literature":[38],"review":[39,123],"on":[40,120,172],"current":[42,75,147],"status":[43,148],"this":[45],"critical":[46],"mechanism.":[47],"It":[48],"discusses":[49],"its":[50],"major":[51,81],"challenges":[52,158],"and":[53,85,99,116,135,149,168,188],"how":[54,173],"it":[55],"can":[56],"be":[57,161],"enhanced":[58],"into":[59],"comprehensive":[61,177],"mechanism":[62],"dealing":[63],"with":[64,164],"issues":[66],"in":[67],"various":[68],"contexts.":[69],"First,":[70],"paper":[72],"elucidates":[73],"landscape":[76],"safeguarding":[78],"mechanisms":[79],"that":[80,104,159],"LLM":[82],"service":[83],"providers":[84],"open-source":[87],"community":[88],"employ.":[89],"is":[91],"followed":[92],"by":[93,165],"techniques":[95,124,142],"evaluate,":[97],"analyze,":[98],"enhance":[100],"some":[101],"(un)desirable":[102],"properties":[103],"guardrail":[106,178],"might":[107],"want":[108],"enforce,":[110],"such":[111],"hallucinations,":[113],"fairness,":[114],"privacy,":[115],"so":[117],"on.":[118],"Based":[119],"them,":[121],"we":[122,154],"circumvent":[126],"these":[127],"controls":[128],"(i.e.,":[129],"attacks),":[130],"defend":[132],"attacks,":[134],"reinforce":[137],"guardrails.":[139],"While":[140],"mentioned":[143],"above":[144],"represent":[145],"active":[151],"research":[152],"trends,":[153],"also":[155],"discuss":[156],"several":[157],"cannot":[160],"easily":[162],"dealt":[163],"methods":[167],"present":[169],"our":[170],"vision":[171],"implement":[175],"through":[179],"full":[181],"consideration":[182],"multi-disciplinary":[184],"approach,":[185],"neural-symbolic":[186],"method,":[187],"systems":[189],"development":[190],"lifecycle.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":39},{"year":2025,"cited_by_count":15}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-17T00:00:00"}