{"id":"https://openalex.org/W4412888090","doi":"https://doi.org/10.18653/v1/2025.findings-acl.704","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","display_name":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888090","doi":"https://doi.org/10.18653/v1/2025.findings-acl.704"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.704","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.704","pdf_url":"https://aclanthology.org/2025.findings-acl.704.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.704.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181324","display_name":"Xiaofei Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofei Wen","raw_affiliation_strings":["University of California , Davis University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Davis University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181325","display_name":"Wenxuan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenxuan Zhou","raw_affiliation_strings":["University of California , Davis University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Davis University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181326","display_name":"Wenjie Jacky Mo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjie Jacky Mo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119181327","display_name":"Muhao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhao Chen","raw_affiliation_strings":["University of California , Davis University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Davis University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.1032759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13698","last_page":"13713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11715","display_name":"Education and Critical Thinking Development","score":0.274399995803833,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11715","display_name":"Education and Critical Thinking Development","score":0.274399995803833,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13081","display_name":"Digital Education and Society","score":0.24199999868869781,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.5031883120536804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5031883120536804}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.704","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.704","pdf_url":"https://aclanthology.org/2025.findings-acl.704.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.704","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.704","pdf_url":"https://aclanthology.org/2025.findings-acl.704.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/G4706632707","display_name":"Proto-OKN Theme 1: Knowledge Graph Construction for Resilient, Trustworthy, and Secure Software Supply Chains","funder_award_id":"2333736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6584218474","display_name":null,"funder_award_id":"HR00112490370","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888090.pdf","grobid_xml":"https://content.openalex.org/works/W4412888090.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":{"Ensuring":[0],"the":[1,58,65,76],"safety":[2,31,53,72,114],"of":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"is":[8],"critical":[9],"as":[10],"they":[11],"are":[12],"deployed":[13],"in":[14],"real-world":[15],"applications.Existing":[16],"guardrails":[17],"rely":[18],"on":[19,55,70],"rule-based":[20],"filtering":[21],"or":[22],"single-pass":[23],"classification,":[24],"limiting":[25],"their":[26],"ability":[27,62],"to":[28,85],"handle":[29],"nuanced":[30,113],"violations.To":[32],"address":[33],"this,":[34],"we":[35],"propose":[36],"THINKGUARD,":[37],"a":[38],"critique-augmented":[39,56],"guardrail":[40],"model":[41],"that":[42,105],"distills":[43],"knowledge":[44],"from":[45],"high-capacity":[46],"LLMs":[47],"by":[48,92,97],"generating":[49],"structured":[50,106],"critiques":[51,107],"alongside":[52],"labels.Fine-tuned":[54],"data,":[57],"captured":[59],"deliberative":[60],"thinking":[61],"drastically":[63],"enhances":[64],"guardrail's":[66],"cautiousness":[67],"and":[68,80,94,112],"interpretability.Evaluated":[69],"multiple":[71],"benchmarks,":[73],"THINKGUARD":[74,89],"achieves":[75],"highest":[77],"average":[78],"F1":[79,96],"AUPRC,":[81],"outperforming":[82],"all":[83],"baselines.Compared":[84],"LLaMA":[86],"Guard":[87],"3,":[88],"improves":[90],"accuracy":[91],"16.1%":[93],"macro":[95],"27.0%.Moreover,":[98],"it":[99],"surpasses":[100],"label-only":[101],"fine-tuned":[102],"models,":[103],"confirming":[104],"enhance":[108],"both":[109],"classification":[110],"precision":[111],"reasoning":[115],"while":[116],"maintaining":[117],"computational":[118],"efficiency.":[119]},"counts_by_year":[],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}
