{"id":"https://openalex.org/W4408356772","doi":"https://doi.org/10.1109/icassp49660.2025.10890844","title":"Diversity Seeking Techniques for Red-Teaming Large Language Models","display_name":"Diversity Seeking Techniques for Red-Teaming Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356772","doi":"https://doi.org/10.1109/icassp49660.2025.10890844"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004040237","display_name":"Seok\u2010Han Lee","orcid":"https://orcid.org/0009-0009-1385-2468"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokhan Lee","raw_affiliation_strings":["Korea University,Dept. Computer Science and Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Dept. Computer Science and Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058649200","display_name":"Bonhwa Ku","orcid":"https://orcid.org/0000-0001-7064-2074"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bonhwa Ku","raw_affiliation_strings":["Korea University,Machine Learning Big Data Institute,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Machine Learning Big Data Institute,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["Korea University,Dept. Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Dept. Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79220524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9887999892234802,"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":0.9887999892234802,"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":0.9434000253677368,"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/diversity","display_name":"Diversity (politics)","score":0.7376300096511841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6387573480606079},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36856192350387573},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.1405855417251587},{"id":"https://openalex.org/keywords/anthropology","display_name":"Anthropology","score":0.05625388026237488}],"concepts":[{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7376300096511841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387573480606079},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36856192350387573},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.1405855417251587},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.05625388026237488}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3174544005","https://openalex.org/W4385894687","https://openalex.org/W4411244884","https://openalex.org/W6675795288","https://openalex.org/W6676385548","https://openalex.org/W6677916085","https://openalex.org/W6771440932","https://openalex.org/W6781156367","https://openalex.org/W6796203516","https://openalex.org/W6811522774","https://openalex.org/W6846587224","https://openalex.org/W6856096788","https://openalex.org/W6860126982","https://openalex.org/W6869546507","https://openalex.org/W6929595913"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1,42],"paper,":[2],"we":[3,58],"present":[4],"new":[5,94],"techniques":[6,132],"for":[7,41,67],"increasing":[8],"the":[9,22,46,64,87,109,115,127,138],"diversity":[10,141],"of":[11,24,126,129,142],"red-teaming":[12],"prompts":[13,40,68,143],"generated":[14,144],"by":[15,62,145],"automated":[16],"machine":[17],"learning-based":[18],"methods,":[19],"thereby":[20],"enabling":[21],"discovery":[23],"more":[25],"vulnerabilities":[26],"in":[27,45,105,117,123],"large":[28],"language":[29],"models.":[30],"Using":[31],"reinforcement":[32,147],"learning":[33,148],"to":[34,37,50,91,114,119,136],"train":[35],"models":[36,47,104],"output":[38],"effective":[39],"task":[43],"results":[44],"converging":[48],"deterministically":[49],"a":[51,78,82],"single":[52],"output.":[53],"Our":[54,96,131],"first":[55],"technique,":[56,98],"which":[57],"term":[59],"Defender,":[60],"acts":[61],"blocking":[63],"reward":[65,88,116],"signal":[66],"that":[69,85],"have":[70],"already":[71],"been":[72],"discovered,":[73],"thus":[74],"making":[75],"what":[76],"was":[77],"stationary":[79],"problem":[80,84],"into":[81],"non-stationary":[83],"compels":[86],"maximizing":[89],"algorithm":[90],"continually":[92],"seek":[93],"prompts.":[95,130],"second":[97],"Teamplay,":[99],"trains":[100],"two":[101],"prompt":[102],"generation":[103],"tandem":[106],"and":[107,140],"adds":[108],"KL":[110],"divergence":[111],"between":[112],"them":[113,121],"order":[118],"make":[120],"search":[122],"disparate":[124],"regions":[125],"space":[128],"are":[133],"shown":[134],"experimentally":[135],"increase":[137],"effectiveness":[139],"existing":[146],"baselines.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}