{"id":"https://openalex.org/W4405181259","doi":"https://doi.org/10.1145/3658644.3690217","title":"A Causal Explainable Guardrails for Large Language Models","display_name":"A Causal Explainable Guardrails for Large Language Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4405181259","doi":"https://doi.org/10.1145/3658644.3690217"},"language":"en","primary_location":{"id":"doi:10.1145/3658644.3690217","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690217","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690217","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690217","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008967163","display_name":"Zhixuan Chu","orcid":"https://orcid.org/0000-0001-6075-1816"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixuan Chu","raw_affiliation_strings":["Zhejiang University & State Key Laboratory of Blockchain and Data Security, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6075-1816","affiliations":[{"raw_affiliation_string":"Zhejiang University & State Key Laboratory of Blockchain and Data Security, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323010","display_name":"Yan Wang","orcid":"https://orcid.org/0009-0006-2938-357X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-2938-357X","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430936","display_name":"Longfei Li","orcid":"https://orcid.org/0000-0002-9263-7011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longfei Li","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9263-7011","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422345","display_name":"Zhibo Wang","orcid":"https://orcid.org/0000-0002-5804-3279"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5804-3279","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043524348","display_name":"Zhan Qin","orcid":"https://orcid.org/0000-0001-7872-6969"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Qin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7872-6969","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000596496","display_name":"Kui Ren","orcid":"https://orcid.org/0000-0003-3441-6277"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Ren","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3441-6277","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4892,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9162839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1136","last_page":"1150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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":0.996999979019165,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.6346330642700195},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5153181552886963},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.46499103307724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3817974627017975},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3739910125732422},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2558530271053314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6346330642700195},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5153181552886963},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.46499103307724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817974627017975},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3739910125732422},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2558530271053314},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658644.3690217","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690217","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690217","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3658644.3690217","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658644.3690217","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658644.3690217","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405181259.pdf","grobid_xml":"https://content.openalex.org/works/W4405181259.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1516659296","https://openalex.org/W2799915114","https://openalex.org/W3080837820","https://openalex.org/W3123340107","https://openalex.org/W3135734416","https://openalex.org/W3171375092","https://openalex.org/W3171442082","https://openalex.org/W3202070718","https://openalex.org/W4200633747","https://openalex.org/W4212774754","https://openalex.org/W4226278401","https://openalex.org/W4281657280","https://openalex.org/W4299515571","https://openalex.org/W4365799947","https://openalex.org/W4385734253","https://openalex.org/W4388230841","https://openalex.org/W4390806447","https://openalex.org/W4393156838","https://openalex.org/W4394877201","https://openalex.org/W4401863345","https://openalex.org/W4404534210","https://openalex.org/W6839328737"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W2058303877"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"impressive":[6],"performance":[7],"in":[8,76,99],"natural":[9],"language":[10],"tasks,":[11],"but":[12],"their":[13],"outputs":[14],"can":[15,45],"exhibit":[16],"undesirable":[17],"attributes":[18,28,104],"or":[19],"biases.":[20,107],"Existing":[21],"methods":[22],"for":[23],"steering":[24,37,52,74,93,100],"LLMs":[25,101,116],"toward":[26,102],"desired":[27,103,120],"often":[29],"assume":[30],"unbiased":[31,73,92],"representations":[32,41,75],"and":[33,68,81,114],"rely":[34],"solely":[35],"on":[36],"prompts.":[38],"However,":[39],"the":[40,51,83,89],"learned":[42],"from":[43],"pre-training":[44],"introduce":[46],"semantic":[47],"biases":[48],"that":[49,64,117],"influence":[50],"process,":[53],"leading":[54],"to":[55,71,111],"suboptimal":[56],"results.":[57],"We":[58],"propose":[59],"LLMGuardrail,":[60],"a":[61],"novel":[62],"framework":[63],"incorporates":[65],"causal":[66],"analysis":[67],"adversarial":[69],"learning":[70],"obtain":[72],"LLMs.":[77],"LLMGuardrail":[78],"systematically":[79],"identifies":[80],"blocks":[82],"confounding":[84],"effects":[85],"of":[86,91],"biases,":[87],"enabling":[88],"extraction":[90],"representations.":[94],"Experiments":[95],"demonstrate":[96],"LLMGuardrail's":[97],"effectiveness":[98],"while":[105],"mitigating":[106],"Our":[108],"work":[109],"contributes":[110],"developing":[112],"safe":[113],"reliable":[115],"align":[118],"with":[119],"attributes.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}