{"id":"https://openalex.org/W4412888295","doi":"https://doi.org/10.18653/v1/2025.findings-acl.529","title":"Weak-to-Strong Honesty Alignment via Learning-to-Rank Supervision","display_name":"Weak-to-Strong Honesty Alignment via Learning-to-Rank Supervision","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888295","doi":"https://doi.org/10.18653/v1/2025.findings-acl.529"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.529","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.529","pdf_url":"https://aclanthology.org/2025.findings-acl.529.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.529.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181396","display_name":"YunfanXie YunfanXie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YunfanXie YunfanXie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089307887","display_name":"Lixin Zou","orcid":"https://orcid.org/0000-0001-6755-871X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lixin Zou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073050929","display_name":"Dan Luo","orcid":"https://orcid.org/0000-0003-2053-2242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055581923","display_name":"Min Tang","orcid":"https://orcid.org/0000-0002-3995-1474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100734069","display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0003-3144-6374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenliang Li","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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83369382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"10154","last_page":"10168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9585000276565552,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9585000276565552,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9122999906539917,"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/honesty","display_name":"Honesty","score":0.9187976121902466},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6763103604316711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5699340105056763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3436301350593567},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3079398274421692},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.19146743416786194},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14604046940803528}],"concepts":[{"id":"https://openalex.org/C2777293324","wikidata":"https://www.wikidata.org/wiki/Q337349","display_name":"Honesty","level":2,"score":0.9187976121902466},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6763103604316711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5699340105056763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3436301350593567},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3079398274421692},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.19146743416786194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14604046940803528},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.529","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.529","pdf_url":"https://aclanthology.org/2025.findings-acl.529.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.529","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.529","pdf_url":"https://aclanthology.org/2025.findings-acl.529.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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4169049969","display_name":null,"funder_award_id":"2022YFB3102900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7817342302","display_name":null,"funder_award_id":"U23A20305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8503653758","display_name":null,"funder_award_id":"254000510007","funder_id":"https://openalex.org/F4320327776","funder_display_name":"Innovation Scientists and Technicians Troop Construction Projects of Henan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327776","display_name":"Innovation Scientists and Technicians Troop Construction Projects of Henan Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888295.pdf","grobid_xml":"https://content.openalex.org/works/W4412888295.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/W2368490655","https://openalex.org/W2369889065","https://openalex.org/W2379032202","https://openalex.org/W2376101501","https://openalex.org/W2374095024","https://openalex.org/W2361112116","https://openalex.org/W2382363130"],"abstract_inverted_index":{"Honest":[0],"alignment":[1,167],"refers":[2],"to":[3,10,19,46,79,91,98,119,129,148,152],"the":[4,36,43,55,72,83,100,111,116,131,145,150,157],"ability":[5],"of":[6],"a":[7,61,88,93],"language":[8],"model":[9,77],"truthfully":[11],"convey":[12],"its":[13,121],"knowledge":[14],"limitations":[15],"by":[16],"appropriately":[17],"refusing":[18],"answer":[20],"questions":[21],"when":[22,49],"it":[23,143],"lacks":[24],"sufficient":[25],"information.Existing":[26],"solutions,":[27],"such":[28],"as":[29],"prompt":[30],"engineering":[31],"and":[32],"fine-tuning,":[33],"face":[34],"limitations:":[35],"former":[37],"provides":[38],"only":[39,125],"marginal":[40],"improvements,":[41],"while":[42],"latter":[44],"struggles":[45],"enhance":[47],"honesty":[48,66],"annotated":[50],"data":[51,128],"is":[52],"scarce.To":[53],"overcome":[54],"above":[56],"limitations,":[57],"we":[58,70,86,114],"propose":[59],"WHAT,":[60],"novel":[62],"framework":[63],"that":[64],"enhances":[65],"through":[67,108],"weak-to-strong":[68],"generalization.Specifically,":[69],"train":[71,92,130],"strong":[73,112,146],"LLMs":[74,147],"under":[75],"weak":[76,84,132],"supervision":[78],"improve":[80],"their":[81],"honesty.For":[82],"model,":[85,134],"employ":[87],"learning-to-rank":[89],"strategy":[90],"\"honest":[94],"head\",":[95],"which":[96],"learns":[97],"select":[99],"most":[101],"honest":[102,133,166],"response":[103],"among":[104],"model's":[105],"outputs":[106],"generated":[107],"beam":[109],"search.For":[110],"LLM,":[113],"leverage":[115],"self-labeled":[117],"dataset":[118],"update":[120],"parameters.Our":[122],"proposal":[123],"requires":[124],"minimal":[126],"training":[127],"yet":[135],"achieve":[136],"decent":[137],"performance":[138],"for":[139],"labeling":[140],"data.In":[141],"addition,":[142],"enables":[144],"have":[149],"capabilities":[151],"generalize":[153],"even":[154,171],"facing":[155],"with":[156,172],"flawed":[158],"label":[159],"data.Extensive":[160],"experiments":[161],"show":[162],"WHAT":[163],"significantly":[164],"boosts":[165],"in":[168],"large":[169],"models":[170],"limited":[173],"labeled":[174],"data.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}