{"id":"https://openalex.org/W4416036490","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1003","title":"Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context","display_name":"Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036490","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1003"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1003","pdf_url":"https://aclanthology.org/2025.emnlp-main.1003.pdf","source":null,"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1003.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100360077","display_name":"Ruikang K. Wang","orcid":"https://orcid.org/0000-0001-5169-8822"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rushi Wang","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117698874","display_name":"Jin Liu","orcid":"https://orcid.org/0000-0001-6915-6183"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiateng Liu","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100769510","display_name":"Cheng Qian","orcid":"https://orcid.org/0000-0003-2249-4681"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Qian","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070990866","display_name":"Yifan Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Shen","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082866231","display_name":"Yanzhou Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhou Pan","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041660006","display_name":"Zhaozhuo Xu","orcid":"https://orcid.org/0000-0001-9555-1830"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaozhuo Xu","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016943900","display_name":"Ahmed Abbasi","orcid":"https://orcid.org/0000-0001-7698-7794"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Abbasi","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113307622","display_name":"Heng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024939674","display_name":"Denghui Zhang","orcid":"https://orcid.org/0009-0004-2606-3234"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denghui Zhang","raw_affiliation_strings":["~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology"],"affiliations":[{"raw_affiliation_string":"~University of Illinois Urbana -Champaign | Google LLC . University of Notre Dame } Stevens Institute of Technology","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100360077"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18394422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19821","last_page":"19856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3513000011444092,"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":0.3513000011444092,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.08370000123977661,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.06830000132322311,"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/context","display_name":"Context (archaeology)","score":0.6972000002861023},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3880999982357025},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6972000002861023},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3813000023365021},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.37700000405311584},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3711000084877014},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.29249998927116394},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26809999346733093},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.26510000228881836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1003","pdf_url":"https://aclanthology.org/2025.emnlp-main.1003.pdf","source":null,"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1003","pdf_url":"https://aclanthology.org/2025.emnlp-main.1003.pdf","source":null,"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036490.pdf","grobid_xml":"https://content.openalex.org/works/W4416036490.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rushi":[0],"Wang,":[1],"Jiateng":[2],"Liu,":[3],"Cheng":[4],"Qian,":[5],"Yifan":[6],"Shen,":[7],"Yanzhou":[8],"Pan,":[9],"Zhaozhuo":[10],"Xu,":[11],"Ahmed":[12],"Abbasi,":[13],"Heng":[14],"Ji,":[15],"Denghui":[16],"Zhang.":[17],"Proceedings":[18],"of":[19],"the":[20],"2025":[21],"Conference":[22],"on":[23],"Empirical":[24],"Methods":[25],"in":[26],"Natural":[27],"Language":[28],"Processing.":[29],"2025.":[30]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-11-08T00:00:00"}
