{"id":"https://openalex.org/W4414590635","doi":"https://doi.org/10.18653/v1/2026.acl-long.197","title":"Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs","display_name":"Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414590635","doi":"https://doi.org/10.18653/v1/2026.acl-long.197"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.197","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.197","pdf_url":"https://aclanthology.org/2026.acl-long.197.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.197.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119757499","display_name":"Shei Pern Chua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shei Pern Chua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119757500","display_name":"Zhen Leng Thai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Leng Thai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Jun Teh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Jun Teh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119757502","display_name":"Xiao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qibing Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qibing Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xiaolin Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00274204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4275","last_page":"4310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11762","display_name":"Law, Economics, and Judicial Systems","score":0.9585000276565552,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11762","display_name":"Law, Economics, and Judicial Systems","score":0.9585000276565552,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11058","display_name":"Ethics in Business and Education","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13851","display_name":"Law, AI, and Intellectual Property","score":0.9319999814033508,"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/vulnerability","display_name":"Vulnerability (computing)","score":0.6744999885559082},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5751000046730042},{"id":"https://openalex.org/keywords/ethical-theories","display_name":"Ethical theories","score":0.4562000036239624},{"id":"https://openalex.org/keywords/motivated-reasoning","display_name":"Motivated reasoning","score":0.4065000116825104},{"id":"https://openalex.org/keywords/poison-control","display_name":"Poison control","score":0.31859999895095825},{"id":"https://openalex.org/keywords/ethical-issues","display_name":"Ethical issues","score":0.30979999899864197},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2978000044822693}],"concepts":[{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6744999885559082},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C2910408888","wikidata":"https://www.wikidata.org/wiki/Q9465","display_name":"Ethical theories","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4260999858379364},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.4065000116825104},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3856000006198883},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C2986663376","wikidata":"https://www.wikidata.org/wiki/Q9465","display_name":"Ethical issues","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C2777745021","wikidata":"https://www.wikidata.org/wiki/Q646102","display_name":"Consequentialism","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C9158031","wikidata":"https://www.wikidata.org/wiki/Q6909140","display_name":"Moral reasoning","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C200113983","wikidata":"https://www.wikidata.org/wiki/Q48324","display_name":"Morality","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C190253527","wikidata":"https://www.wikidata.org/wiki/Q295354","display_name":"Law and economics","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.26899999380111694},{"id":"https://openalex.org/C2994432249","wikidata":"https://www.wikidata.org/wiki/Q9465","display_name":"Ethical theory","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C139621336","wikidata":"https://www.wikidata.org/wiki/Q3190382","display_name":"Economic Justice","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.197","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.197","pdf_url":"https://aclanthology.org/2026.acl-long.197.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.05367","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.05367","pdf_url":"https://arxiv.org/pdf/2509.05367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2509.05367","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.05367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.197","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.197","pdf_url":"https://aclanthology.org/2026.acl-long.197.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3710292167","display_name":null,"funder_award_id":"U2341228","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G743810131","display_name":null,"funder_award_id":"62576187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8495192761","display_name":null,"funder_award_id":"JYB2025XDXM504","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320313434","display_name":"Institute for Catastrophic Loss Reduction","ror":null},{"id":"https://openalex.org/F4320314997","display_name":"Strong","ror":"https://ror.org/041vyzr56"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414590635.pdf","grobid_xml":"https://content.openalex.org/works/W4414590635.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Warning:":[0],"This":[1],"paper":[2],"contains":[3],"potentially":[4],"offensive":[5],"and":[6,109],"harmful":[7,58,82,107,118],"text.Large":[8],"Language":[9],"Model":[10],"safety":[11],"alignment":[12],"predominantly":[13],"operates":[14],"on":[15,88],"a":[16,43,52,97,121],"binary":[17],"assumption":[18],"that":[19,56,100,105,112],"requests":[20,59],"are":[21],"either":[22],"safe":[23],"or":[24],"unsafe.This":[25],"classification":[26],"proves":[27],"insufficient":[28],"when":[29],"models":[30,71],"encounter":[31],"ethical":[32,61,77,114],"dilemmas,":[33],"where":[34],"the":[35,75],"capacity":[36],"to":[37,80],"reason":[38],"through":[39,50],"moral":[40],"trade-offs":[41],"creates":[42],"distinct":[44],"attack":[45,65],"surface.We":[46],"formalize":[47],"this":[48],"vulnerability":[49],"TRIAL,":[51],"multi-turn":[53],"red-teaming":[54],"methodology":[55],"embeds":[57],"within":[60],"framings.TRIAL":[62],"achieves":[63],"high":[64],"success":[66],"rates":[67],"across":[68],"most":[69],"tested":[70],"by":[72],"systematically":[73],"exploiting":[74],"model's":[76],"reasoning":[78],"capabilities":[79],"frame":[81],"actions":[83],"as":[84],"morally":[85],"necessary":[86],"compromises.Building":[87],"these":[89],"insights,":[90],"we":[91],"introduce":[92],"ERR":[93],"(Ethical":[94],"Reasoning":[95],"Robustness),":[96],"defense":[98,128],"framework":[99],"distinguishes":[101],"between":[102],"instrumental":[103],"responses":[104,111],"enable":[106],"outcomes":[108],"explanatory":[110],"analyze":[113],"frameworks":[115],"without":[116],"endorsing":[117],"acts.ERR":[119],"employs":[120],"Layer-Stratified":[122],"Harm-Gated":[123],"LoRA":[124],"architecture,":[125],"achieving":[126],"robust":[127],"against":[129],"reasoning-based":[130],"attacks":[131],"while":[132],"preserving":[133],"model":[134],"utility.":[135]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
