{"id":"https://openalex.org/W4404782303","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.868","title":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","display_name":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782303","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.868"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.868","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.emnlp-main.868","pdf_url":"https://aclanthology.org/2024.emnlp-main.868.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":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.emnlp-main.868.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101958947","display_name":"Tzu-Han Lin","orcid":"https://orcid.org/0000-0003-1684-8025"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-Han Lin","raw_affiliation_strings":["National Taiwan University , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029645824","display_name":"Chen-An Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen-An Li","raw_affiliation_strings":["National Taiwan University , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["National Taiwan University , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027052085","display_name":"Yun-Nung Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yun-Nung Chen","raw_affiliation_strings":["National Taiwan University , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University , Taipei , Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22708264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15506","last_page":"15524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9689000248908997,"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":0.9689000248908997,"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":0.9623000025749207,"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":0.7430647611618042},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5722454786300659},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4794794023036957},{"id":"https://openalex.org/keywords/domain-model","display_name":"Domain model","score":0.4360455274581909},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4144083559513092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3603270351886749},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3214142620563507},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1833040714263916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430647611618042},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5722454786300659},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4794794023036957},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.4360455274581909},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4144083559513092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3603270351886749},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3214142620563507},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1833040714263916},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.868","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.emnlp-main.868","pdf_url":"https://aclanthology.org/2024.emnlp-main.868.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":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.868","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.emnlp-main.868","pdf_url":"https://aclanthology.org/2024.emnlp-main.868.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":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316499","display_name":"National Applied Research Laboratories","ror":"https://ror.org/05wcstg80"},{"id":"https://openalex.org/F4320323900","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782303.pdf","grobid_xml":"https://content.openalex.org/works/W4404782303.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4232844628","https://openalex.org/W2374471852","https://openalex.org/W1583422155","https://openalex.org/W2166877816","https://openalex.org/W1587887330","https://openalex.org/W2741239878","https://openalex.org/W1649619740","https://openalex.org/W2479071323","https://openalex.org/W2349037640","https://openalex.org/W2917572814"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"from":[2],"human":[3],"feedback":[4],"(RLHF)":[5],"is":[6,20,34],"a":[7,21,58,66,84],"popular":[8],"strategy":[9],"for":[10,30,40],"aligning":[11],"large":[12],"language":[13],"models":[14,33],"(LLMs)":[15],"with":[16],"desired":[17],"behaviors.Reward":[18],"modeling":[19],"crucial":[22],"step":[23],"in":[24],"RLHF.However,":[25],"collecting":[26],"paired":[27],"preference":[28],"data":[29],"training":[31],"reward":[32,68],"often":[35],"costly":[36],"and":[37,82],"time-consuming,":[38],"especially":[39],"domainspecific":[41],"preferences":[42],"requiring":[43],"expert":[44],"annotation.To":[45],"address":[46],"this":[47],"challenge,":[48],"we":[49],"propose":[50],"the":[51,88,94],"Domain":[52],"knowledge":[53,64],"merged":[54],"Reward":[55],"Model":[56],"(DogeRM),":[57],"novel":[59],"framework":[60],"that":[61,75],"integrates":[62],"domain-specific":[63],"into":[65],"general":[67],"model":[69,71,91,99],"by":[70],"merging.The":[72],"experiments":[73],"demonstrate":[74],"DogeRM":[76],"enhances":[77],"performance":[78],"across":[79],"different":[80],"benchmarks":[81],"provide":[83],"detailed":[85],"analysis":[86],"showcasing":[87],"effects":[89],"of":[90,97],"merging,":[92],"showing":[93],"great":[95],"potential":[96],"facilitating":[98],"alignment.1":[100]},"counts_by_year":[],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}