{"id":"https://openalex.org/W4412888494","doi":"https://doi.org/10.18653/v1/2025.findings-acl.344","title":"RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations","display_name":"RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888494","doi":"https://doi.org/10.18653/v1/2025.findings-acl.344"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.344","pdf_url":"https://aclanthology.org/2025.findings-acl.344.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.344.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103325805","display_name":"Lian Yan","orcid":"https://orcid.org/0009-0008-1695-2467"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068465714","display_name":"Chen Tang","orcid":"https://orcid.org/0000-0003-1188-4393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012962057","display_name":"Yi Guan","orcid":"https://orcid.org/0000-0003-3618-6719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069527951","display_name":"Haotian Wang","orcid":"https://orcid.org/0000-0002-0362-181X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haotian Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090916803","display_name":"Songyuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songyuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108111569","display_name":"Haifeng Liu","orcid":"https://orcid.org/0009-0003-4031-272X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haifeng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103839474","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-8943-1688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064238181","display_name":"Jingchi Jiang","orcid":"https://orcid.org/0000-0003-2167-4082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingchi Jiang","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":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6619","last_page":"6633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9900000095367432,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9900000095367432,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9539999961853027,"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":0.9085000157356262,"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":0.7242352962493896},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7127072811126709},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5029584765434265},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.4644489288330078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3967817425727844},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35225576162338257},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21341446042060852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242352962493896},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7127072811126709},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5029584765434265},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.4644489288330078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3967817425727844},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35225576162338257},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21341446042060852}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.344","pdf_url":"https://aclanthology.org/2025.findings-acl.344.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.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.344","pdf_url":"https://aclanthology.org/2025.findings-acl.344.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/G1639125895","display_name":null,"funder_award_id":"72431004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4199735566","display_name":null,"funder_award_id":"72293584","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G432708553","display_name":null,"funder_award_id":"2024ZX01A07","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"},{"id":"https://openalex.org/G8886107574","display_name":null,"funder_award_id":"JD2023GJ01","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"}],"funders":[{"id":"https://openalex.org/F4320317323","display_name":"Key Research and Development Program of Heilongjiang","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888494.pdf","grobid_xml":"https://content.openalex.org/works/W4412888494.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Reinforcement":[0,74,100],"Learning":[1,75,101],"from":[2,65,76,102],"Human":[3],"Feedback":[4,79,104],"(RLHF)":[5],"has":[6],"been":[7],"shown":[8],"to":[9,32,90],"effectively":[10],"align":[11],"large":[12],"language":[13],"models":[14],"(LLMs)":[15],"with":[16,121],"human":[17,22,55,109],"knowledge.However,":[18],"the":[19,51,95,115,170],"lack":[20],"of":[21,97],"preference":[23,126],"labels":[24],"remains":[25],"a":[26,33,39,81],"significant":[27],"bottleneck":[28],"when":[29],"applying":[30],"RLHF":[31,37],"downstream":[34],"domain.Humans":[35],"in":[36,42,94,112,173],"play":[38],"critical":[40],"role":[41],"injecting":[43],"reasoning":[44,52,62],"preferences":[45],"into":[46,135],"LLM,":[47],"and":[48,88,138,147,152,159],"we":[49,72],"assume":[50],"process":[53],"underlying":[54],"assessments":[56],"may":[57],"potentially":[58],"be":[59],"replaced":[60],"by":[61,69,141],"pathways":[63],"derived":[64],"Knowledge":[66,77],"Graphs":[67],"(KGs).Inspired":[68],"this":[70],"assumption,":[71],"propose":[73],"Graph":[78],"(RLKGF),":[80],"novel":[82],"method":[83],"that":[84,166],"leverages":[85],"KG":[86],"semantics":[87],"structure":[89],"derive":[91],"RL":[92],"rewards":[93,140],"absence":[96],"manual":[98],"annotations.Unlike":[99],"AI":[103],"(RLAIF),":[105],"RLKGF":[106,167],"directly":[107],"integrates":[108],"priors":[110],"encoded":[111],"KGs":[113],"as":[114],"reward":[116,129],"model,":[117],"aligning":[118],"LLM":[119,175],"responses":[120],"expert":[122],"knowledge":[123,136],"without":[124],"additional":[125],"labeling":[127],"or":[128],"model":[130],"training.RLKGF":[131],"structures":[132],"contextrelevant":[133],"facts":[134],"subgraphs":[137],"defines":[139],"simulating":[142],"information":[143],"flow":[144],"across":[145],"semantic":[146],"logical":[148],"connections":[149],"between":[150],"question":[151],"candidate":[153],"response":[154],"entities.Experiments":[155],"on":[156],"three":[157],"public":[158],"one":[160],"private":[161],"medical":[162],"dialogue":[163],"dataset":[164],"demonstrate":[165],"significantly":[168],"outperforms":[169],"competitive":[171],"RLAIF":[172],"improving":[174],"diagnostic":[176],"accuracy.The":[177],"code":[178],"is":[179],"available":[180],"at":[181],"https:":[182],"//github.com/YanPioneer/RLKGF.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}