{"id":"https://openalex.org/W7126088995","doi":"https://doi.org/10.1109/acompa69200.2025.00009","title":"Reward Design for Reinforcement Learning in the Development of Large Language Models","display_name":"Reward Design for Reinforcement Learning in the Development of Large Language Models","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W7126088995","doi":"https://doi.org/10.1109/acompa69200.2025.00009"},"language":null,"primary_location":{"id":"doi:10.1109/acompa69200.2025.00009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acompa69200.2025.00009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Advanced Computing and Analytics (ACOMPA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102026883","display_name":"Thanh Thi Nguyen","orcid":"https://orcid.org/0009-0007-8396-1737"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thanh Thi Nguyen","raw_affiliation_strings":["Monash University,AiLECS Lab,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,AiLECS Lab,Melbourne,Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048815917","display_name":"Campbell Wilson","orcid":"https://orcid.org/0000-0001-5144-411X"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Campbell Wilson","raw_affiliation_strings":["Monash University,AiLECS Lab,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,AiLECS Lab,Melbourne,Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059284047","display_name":"Janis Dalins","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Janis Dalins","raw_affiliation_strings":["Monash University,AiLECS Lab,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,AiLECS Lab,Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61644359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.3529999852180481,"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"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.3529999852180481,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.08299999684095383,"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/T10028","display_name":"Topic Modeling","score":0.061799999326467514,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8023999929428101},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6114000082015991},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39259999990463257},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.35659998655319214},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.295199990272522}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8023999929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.660099983215332},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2718000113964081}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acompa69200.2025.00009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acompa69200.2025.00009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Advanced Computing and Analytics (ACOMPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2902907165","https://openalex.org/W2908261578","https://openalex.org/W4383112908","https://openalex.org/W4385245566","https://openalex.org/W4386075632","https://openalex.org/W4389524039","https://openalex.org/W4393763811","https://openalex.org/W4400528355","https://openalex.org/W4401042684","https://openalex.org/W4402364221","https://openalex.org/W4402670760","https://openalex.org/W4402671689","https://openalex.org/W4404545208","https://openalex.org/W4410371768","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3,94],"long":[4],"been":[5,66,95],"utilized":[6,96],"in":[7,51,87,145,164,182],"natural":[8],"language":[9,22],"processing,":[10],"but":[11],"it":[12],"gained":[13],"considerable":[14],"attention":[15],"when":[16],"OpenAI":[17],"introduced":[18],"ChatGPT.":[19],"This":[20,77],"large":[21],"model":[23],"(LLM)":[24],"integrates":[25],"RL":[26,47,70,84,93,144,165],"with":[27,41],"human":[28,42],"feedback":[29],"during":[30],"training":[31,52],"to":[32,71,97,116,121,155,178],"improve":[33,98],"its":[34,39],"performance":[35],"by":[36,55],"adaptively":[37],"aligning":[38],"outputs":[40],"preferences":[43],"and":[44,108],"ethical":[45],"standards.":[46],"was":[48],"also":[49,133,171],"used":[50],"DeepSeek-R1,":[53],"developed":[54],"DeepSeek-AI,":[56],"as":[57,59],"well":[58],"other":[60],"leading":[61],"LLMs.":[62,76],"Numerous":[63],"studies":[64],"have":[65],"undertaken":[67],"on":[68,101,119],"using":[69],"enhance":[72,179],"the":[73,102,123,141,161,167,173],"capabilities":[74,181],"of":[75,82,110,126,143,151,160],"paper":[78],"provides":[79],"an":[80],"overview":[81,159],"various":[83,135],"methodologies":[85],"applied":[86],"LLM":[88,130,147,168,180],"development.":[89,148],"We":[90,132],"examine":[91],"how":[92,120],"LLMs,":[99],"focusing":[100],"reward":[103,127],"design":[104],"perspective.":[105],"The":[106,149],"merits":[107],"drawbacks":[109],"these":[111],"approaches":[112],"are":[113],"thoroughly":[114],"analyzed":[115],"shed":[117],"light":[118],"choose":[122],"appropriate":[124],"type":[125],"for":[128,166,175],"RL-based":[129],"fine-tuning.":[131],"highlight":[134],"research":[136,177],"directions":[137],"that":[138],"can":[139],"leverage":[140],"potential":[142],"advancing":[146],"objective":[150],"this":[152],"work":[153],"is":[154],"deliver":[156],"a":[157],"thorough":[158],"latest":[162],"advancements":[163],"development,":[169],"while":[170],"laying":[172],"foundation":[174],"subsequent":[176],"real-world":[183],"applications.":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-30T00:00:00"}