{"id":"https://openalex.org/W4385894687","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.225","title":"Red Teaming Language Models with Language Models","display_name":"Red Teaming Language Models with Language Models","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385894687","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.225"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.emnlp-main.225","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.225","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.225","pdf_url":"https://aclanthology.org/2022.emnlp-main.225.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.emnlp-main.225.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091112967","display_name":"Ethan Perez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ethan Perez","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040949100","display_name":"Saffron Huang","orcid":"https://orcid.org/0009-0008-2654-5961","observed_orcids":["https://orcid.org/0009-0008-2654-5961"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saffron Huang","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031035504","display_name":"Francis Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francis Song","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051582703","display_name":"Trevor Y. Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Cai","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089972944","display_name":"Roman Ring","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roman Ring","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029807267","display_name":"John Aslanides","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Aslanides","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005117726","display_name":"Amelia Glaese","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amelia Glaese","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003470218","display_name":"Nat McAleese","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nat McAleese","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029611587","display_name":"Geoffrey Irving","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey Irving","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5091112967"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":33.2379,"has_fulltext":true,"cited_by_count":338,"citation_normalized_percentile":{"value":0.99850954,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3419","last_page":"3448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9223999977111816,"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":0.9223999977111816,"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":0.041200000792741776,"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":0.024900000542402267,"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/red-teaming","display_name":"red teaming","score":0.9110000133514404},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.8690000176429749},{"id":"https://openalex.org/keywords/adversarial-evaluation","display_name":"adversarial evaluation","score":0.621999979019165},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.39899998903274536},{"id":"https://openalex.org/keywords/language-model-evaluation","display_name":"language model evaluation","score":0.328000009059906},{"id":"https://openalex.org/keywords/adversarial-prompts","display_name":"adversarial prompts","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6422333121299744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5333279371261597},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4676617681980133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4664219319820404},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4460082948207855},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3647192418575287},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3560556173324585},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.14928728342056274},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12897583842277527}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.emnlp-main.225","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.225","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.225","pdf_url":"https://aclanthology.org/2022.emnlp-main.225.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.emnlp-main.225","doi":"https://doi.org/10.18653/v1/2022.emnlp-main.225","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.emnlp-main.225","pdf_url":"https://aclanthology.org/2022.emnlp-main.225.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2022 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385894687.pdf","grobid_xml":"https://content.openalex.org/works/W4385894687.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1673923490","https://openalex.org/W1841592590","https://openalex.org/W1945616565","https://openalex.org/W2053637704","https://openalex.org/W2096633407","https://openalex.org/W2101105183","https://openalex.org/W2273879499","https://openalex.org/W2274565976","https://openalex.org/W2408141691","https://openalex.org/W2462906003","https://openalex.org/W2468328197","https://openalex.org/W2473418344","https://openalex.org/W2535690855","https://openalex.org/W2570685808","https://openalex.org/W2591984255","https://openalex.org/W2766108848","https://openalex.org/W2770550542","https://openalex.org/W2791170418","https://openalex.org/W2799194071","https://openalex.org/W2890365488","https://openalex.org/W2893240881","https://openalex.org/W2917779306","https://openalex.org/W2938704169","https://openalex.org/W2951328433","https://openalex.org/W2951883832","https://openalex.org/W2952604841","https://openalex.org/W2953981431","https://openalex.org/W2962835266","https://openalex.org/W2963456134","https://openalex.org/W2963903950","https://openalex.org/W2963969878","https://openalex.org/W2964043796","https://openalex.org/W2968297680","https://openalex.org/W2969117066","https://openalex.org/W2970290563","https://openalex.org/W2970630590","https://openalex.org/W2971307358","https://openalex.org/W2972766508","https://openalex.org/W2973379954","https://openalex.org/W2997510038","https://openalex.org/W3031668985","https://openalex.org/W3034850762","https://openalex.org/W3035068109","https://openalex.org/W3035239386","https://openalex.org/W3088599783","https://openalex.org/W3101767999","https://openalex.org/W3103245149","https://openalex.org/W3106051020","https://openalex.org/W3134095442","https://openalex.org/W3134354193","https://openalex.org/W3169306793","https://openalex.org/W3171850892","https://openalex.org/W3172314079","https://openalex.org/W3174057701","https://openalex.org/W3175487198","https://openalex.org/W3179534853","https://openalex.org/W3199369541","https://openalex.org/W3200980294","https://openalex.org/W3201396246","https://openalex.org/W3203534993","https://openalex.org/W3206210649","https://openalex.org/W3207835719","https://openalex.org/W4229907684","https://openalex.org/W4286987939","https://openalex.org/W4287116904","https://openalex.org/W4287674181","https://openalex.org/W4287887244","https://openalex.org/W4288104702","https://openalex.org/W4288376529","https://openalex.org/W4293569541","https://openalex.org/W4294410794","https://openalex.org/W4298845604","https://openalex.org/W4307123345","https://openalex.org/W4308902180","https://openalex.org/W4320013936","https://openalex.org/W4385468994"],"related_works":["https://openalex.org/W4243252198","https://openalex.org/W2118300983","https://openalex.org/W2112962394","https://openalex.org/W3137189469","https://openalex.org/W1872130062","https://openalex.org/W2293457016","https://openalex.org/W159132833","https://openalex.org/W2977842567","https://openalex.org/W2502722637","https://openalex.org/W3198474835"],"abstract_inverted_index":{"Ethan":[0],"Perez,":[1],"Saffron":[2],"Huang,":[3],"Francis":[4],"Song,":[5],"Trevor":[6],"Cai,":[7],"Roman":[8],"Ring,":[9],"John":[10],"Aslanides,":[11],"Amelia":[12],"Glaese,":[13],"Nat":[14],"McAleese,":[15],"Geoffrey":[16],"Irving.":[17],"Proceedings":[18],"of":[19],"the":[20],"2022":[21],"Conference":[22],"on":[23],"Empirical":[24],"Methods":[25],"in":[26],"Natural":[27],"Language":[28],"Processing.":[29],"2022.":[30]},"counts_by_year":[{"year":2026,"cited_by_count":126},{"year":2025,"cited_by_count":93},{"year":2024,"cited_by_count":60},{"year":2023,"cited_by_count":50},{"year":2022,"cited_by_count":9}],"updated_date":"2026-10-10T09:11:00.788812","created_date":"2025-10-10T00:00:00"}