{"id":"https://openalex.org/W4412888656","doi":"https://doi.org/10.18653/v1/2025.findings-acl.339","title":"Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?","display_name":"Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888656","doi":"https://doi.org/10.18653/v1/2025.findings-acl.339"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.339","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.339","pdf_url":"https://aclanthology.org/2025.findings-acl.339.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.339.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090328003","display_name":"Chengda Lu","orcid":"https://orcid.org/0000-0002-9452-4053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengda Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086743235","display_name":"Xiaoyu Fan","orcid":"https://orcid.org/0000-0002-0390-5871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyu Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055065021","display_name":"Yu Huang","orcid":"https://orcid.org/0000-0002-9935-7717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104333316","display_name":"Rongwu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongwu Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101335017","display_name":"Jijie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jijie Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108130042","display_name":"Wei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xu","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":0.17637369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6523","last_page":"6546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12268","display_name":"Deception detection and forensic psychology","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12268","display_name":"Deception detection and forensic psychology","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12520","display_name":"Psychology of Moral and Emotional Judgment","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10565","display_name":"Psychopathy, Forensic Psychiatry, Sexual Offending","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6062273383140564},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.495764821767807},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.39293405413627625},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23587757349014282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6062273383140564},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.495764821767807},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.39293405413627625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23587757349014282},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.339","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.339","pdf_url":"https://aclanthology.org/2025.findings-acl.339.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.339","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.339","pdf_url":"https://aclanthology.org/2025.findings-acl.339.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G366789873","display_name":null,"funder_award_id":"62176135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7422017672","display_name":null,"funder_award_id":"U2268202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888656.pdf","grobid_xml":"https://content.openalex.org/works/W4412888656.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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":{"Jailbreak":[0],"attacks":[1],"have":[2],"been":[3],"observed":[4],"to":[5,36],"largely":[6],"fail":[7],"against":[8],"recent":[9],"reasoning":[10,26,42,55],"models":[11],"enhanced":[12],"by":[13,115],"Chain-of-Thought":[14],"(CoT)":[15],"reasoning.However,":[16],"the":[17,38,63,110],"underlying":[18],"mechanism":[19],"remains":[20],"underexplored,":[21],"and":[22],"relying":[23],"solely":[24],"on":[25,59,62],"capacity":[27],"may":[28],"raise":[29],"security":[30],"concerns.In":[31],"this":[32],"paper,":[33],"we":[34,51,66],"try":[35],"answer":[37],"question:":[39],"Does":[40],"CoT":[41,54],"really":[43],"reduce":[44],"harmfulness":[45,104,112],"from":[46],"jailbreaking?Through":[47],"rigorous":[48],"theoretical":[49,64,78],"analysis,":[50],"demonstrate":[52],"that":[53,109],"has":[56],"dual":[57],"effects":[58],"jailbreaking":[60],"harmfulness.Based":[61],"insights,":[65],"propose":[67],"a":[68],"novel":[69],"jailbreak":[70],"method,":[71],"FICDETAIL,":[72],"whose":[73],"practical":[74],"performance":[75],"validates":[76],"our":[77],"findings.Warning:":[79],"This":[80],"work":[81],"contains":[82],"potentially":[83],"offensive":[84],"LLM-generated":[85],"content.*":[86],"Equal":[87],"contribution.":[88],"1":[89,107],"q":[90],"p":[91],"(P":[92,94,97],")f":[93],")h":[95],"(i)":[96],")":[98],"dP":[99],"J":[100],"Key":[101],"factors":[102],"affecting":[103],"with":[105],"CoT.Proposition":[106],"implies":[108],"expected":[111],"is":[113],"influenced":[114],"several":[116],"crucial":[117],"factors:":[118]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
