{"id":"https://openalex.org/W4395069539","doi":"https://doi.org/10.1109/access.2024.3393245","title":"Beyond Binary Classification: A Fine-Grained Safety Dataset for Large Language Models","display_name":"Beyond Binary Classification: A Fine-Grained Safety Dataset for Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395069539","doi":"https://doi.org/10.1109/access.2024.3393245"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3393245","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3393245","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10507773.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10507773.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051954454","display_name":"Jia Yu","orcid":"https://orcid.org/0009-0001-0801-9692"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Yu","raw_affiliation_strings":["School of Engineering, Zhejiang University, Hangzhou, China","Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-0801-9692","affiliations":[{"raw_affiliation_string":"School of Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425370","display_name":"Long Li","orcid":"https://orcid.org/0000-0002-2697-4546"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Li","raw_affiliation_strings":["School of Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103239171","display_name":"Zhenzhong Lan","orcid":"https://orcid.org/0000-0003-4763-6148"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhong Lan","raw_affiliation_strings":["School of Engineering, Zhejiang University, Hangzhou, China","Westlake University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1114,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80096599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"64717","last_page":"64726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9952999949455261,"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":0.9952999949455261,"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":0.9818999767303467,"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":0.9616000056266785,"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/computer-science","display_name":"Computer science","score":0.7816010117530823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.437951922416687},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43289926648139954},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4316796362400055},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4290086030960083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38264235854148865},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1802675426006317},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1702650785446167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816010117530823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.437951922416687},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43289926648139954},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4316796362400055},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4290086030960083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38264235854148865},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1802675426006317},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1702650785446167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3393245","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3393245","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10507773.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:895c5b3db9fa4f9b85adf83fef608953","is_oa":true,"landing_page_url":"https://doaj.org/article/895c5b3db9fa4f9b85adf83fef608953","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":"IEEE Access, Vol 12, Pp 64717-64726 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3393245","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3393245","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10507773.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395069539.pdf","grobid_xml":"https://content.openalex.org/works/W4395069539.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2566862711","https://openalex.org/W2963351448","https://openalex.org/W3028930880","https://openalex.org/W3100355250","https://openalex.org/W3122890974","https://openalex.org/W3201174429","https://openalex.org/W3207316473","https://openalex.org/W4224308101","https://openalex.org/W4296413526","https://openalex.org/W4296557505","https://openalex.org/W4297813086","https://openalex.org/W4312220150","https://openalex.org/W4365143687","https://openalex.org/W4380136478","https://openalex.org/W4384918448","https://openalex.org/W4385468994","https://openalex.org/W4385571232","https://openalex.org/W4385894687","https://openalex.org/W4387838992","https://openalex.org/W4389519254","https://openalex.org/W4389523771","https://openalex.org/W4394828156","https://openalex.org/W6736461433","https://openalex.org/W6774845726","https://openalex.org/W6779068807","https://openalex.org/W6801617135","https://openalex.org/W6810081322","https://openalex.org/W6810792567","https://openalex.org/W6839459284","https://openalex.org/W6842722019","https://openalex.org/W6852473727","https://openalex.org/W6852874933","https://openalex.org/W6853986894","https://openalex.org/W6854555012","https://openalex.org/W6854866820","https://openalex.org/W6854948896","https://openalex.org/W6857146736"],"related_works":["https://openalex.org/W1993278628","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"excel":[4],"in":[5,34,56,76,185,208,243],"interactive":[6],"chat":[7],"scenarios":[8],"due":[9],"to":[10,22,71,120,124,168,196,224,238],"their":[11,16],"advanced":[12,202],"conversational":[13],"abilities.":[14],"However,":[15],"training":[17],"process":[18],"invariably":[19],"exposes":[20],"them":[21],"a":[23,53,67,135,158,217],"diverse":[24],"range":[25],"of":[26,49,85,95,172,182,188,204,230],"harmful":[27],"or":[28],"toxic":[29],"content,":[30],"posing":[31],"significant":[32],"challenges":[33],"ensuring":[35],"that":[36],"LLM":[37,209],"responses":[38,171],"align":[39],"with":[40,143],"human":[41,93],"ethical":[42],"values.":[43],"Consequently,":[44],"the":[45,64,82,164,170,180,186,205,221,225],"detection":[46],"and":[47,89,112,228,234],"quantification":[48],"adverse":[50],"content":[51,86,101],"remains":[52],"paramount":[54],"issue":[55],"contemporary":[57],"research.":[58],"In":[59,130],"this":[60,214,244],"paper,":[61],"we":[62,97,132,147],"introduce":[63],"SAFE":[65,165],"dataset,":[66,166],"novel":[68],"resource":[69,219],"designed":[70,167],"advance":[72],"safety":[73,144,189],"assessment":[74,190],"research":[75,241],"LLMs.":[77,192,231],"Our":[78,232],"dataset":[79,136,184,215],"extends":[80],"beyond":[81],"binary":[83],"categorization":[84],"into":[87,102],"\u201csafe\u201d":[88],"\u201cunsafe\u201d.":[90],"Drawing":[91],"upon":[92],"interpretations":[94],"safety,":[96],"further":[98],"delineate":[99],"unsafe":[100,126],"six":[103],"granular":[104],"categories:":[105],"Sensitivity,":[106],"Harmfulness,":[107],"Falsehood,":[108],"Information":[109],"Corruption,":[110],"Unnaturalness,":[111],"Deviation":[113],"from":[114],"Instructions.":[115],"This":[116,177],"refined":[117],"classification":[118],"aims":[119],"enhance":[121],"LLMs\u2019":[122],"ability":[123],"discern":[125],"data":[127],"more":[128],"accurately.":[129],"total,":[131],"have":[133,148],"created":[134],"comprising":[137],"52,340":[138],"instruction-response":[139],"pairs,":[140],"each":[141],"annotated":[142],"meta-tags.":[145],"Additionally,":[146],"compiled":[149],"expert":[150],"comparative":[151],"assessments":[152],"for":[153,191,220],"these":[154],"indicators.":[155],"We":[156,212],"developed":[157],"multi-expert":[159],"rating":[160],"model":[161],"trained":[162],"on":[163],"evaluate":[169],"LLMs":[173],"across":[174],"various":[175],"dimensions.":[176],"approach":[178],"highlights":[179],"potential":[181],"our":[183],"realm":[187],"The":[193],"model\u2019s":[194],"capability":[195],"provide":[197],"multi-faceted":[198],"evaluations":[199],"reflects":[200],"an":[201],"understanding":[203],"nuanced":[206],"requirements":[207],"response":[210],"assessment.":[211],"believe":[213],"represents":[216],"valuable":[218],"community,":[222],"contributing":[223],"safe":[226],"development":[227],"deployment":[229],"findings":[233],"resources":[235],"are":[236],"poised":[237],"fuel":[239],"future":[240],"endeavors":[242],"domain.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}