{"id":"https://openalex.org/W4406612587","doi":"https://doi.org/10.1109/wsc63780.2024.10838929","title":"Enhancing Language Model with Both Human and Artificial Intelligence Feedback Data","display_name":"Enhancing Language Model with Both Human and Artificial Intelligence Feedback Data","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406612587","doi":"https://doi.org/10.1109/wsc63780.2024.10838929"},"language":"en","primary_location":{"id":"doi:10.1109/wsc63780.2024.10838929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc63780.2024.10838929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},"type":"article","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/A5108306094","display_name":"Haoting Zhang","orcid":"https://orcid.org/0000-0001-9416-2024"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haoting Zhang","raw_affiliation_strings":["University of California at Berkeley,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085811108","display_name":"Jinghai He","orcid":"https://orcid.org/0000-0002-5458-2048"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinghai He","raw_affiliation_strings":["University of California at Berkeley,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074971120","display_name":"Jingxu Xu","orcid":"https://orcid.org/0000-0002-1327-6490"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingxu Xu","raw_affiliation_strings":["University of California at Berkeley,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100314442","display_name":"Jingshen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingshen Wang","raw_affiliation_strings":["University of California at Berkeley,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002874750","display_name":"Zeyu Zheng","orcid":"https://orcid.org/0000-0001-5653-152X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Zheng","raw_affiliation_strings":["University of California at Berkeley,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108306094"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24049782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7407000064849854,"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":0.7407000064849854,"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":0.6917999982833862,"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":0.7435038685798645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5309977531433105},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4850732386112213},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41400018334388733},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3499244451522827},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.145306795835495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435038685798645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309977531433105},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4850732386112213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41400018334388733},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3499244451522827},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.145306795835495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wsc63780.2024.10838929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc63780.2024.10838929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Winter Simulation Conference (WSC)","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":33,"referenced_works":["https://openalex.org/W1925297253","https://openalex.org/W2113997143","https://openalex.org/W2154397892","https://openalex.org/W2158126207","https://openalex.org/W2160637580","https://openalex.org/W2180251445","https://openalex.org/W2278747027","https://openalex.org/W2529348500","https://openalex.org/W2787894218","https://openalex.org/W2909310974","https://openalex.org/W2922183461","https://openalex.org/W2963292708","https://openalex.org/W3004346979","https://openalex.org/W3006691269","https://openalex.org/W3092934784","https://openalex.org/W3117834163","https://openalex.org/W3132298134","https://openalex.org/W3132310403","https://openalex.org/W3199510319","https://openalex.org/W4210573712","https://openalex.org/W4211042066","https://openalex.org/W4225407174","https://openalex.org/W4229939670","https://openalex.org/W4252698487","https://openalex.org/W4255693858","https://openalex.org/W4288080706","https://openalex.org/W4327742605","https://openalex.org/W4385456846","https://openalex.org/W4388945420","https://openalex.org/W6676105031","https://openalex.org/W6739585900","https://openalex.org/W6852418670","https://openalex.org/W6857830995"],"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":{"The":[0,17,69],"proliferation":[1],"of":[2,19,52,88,95,129],"language":[3,67,131],"models":[4,21,50],"has":[5],"marked":[6],"a":[7,26,60,103],"significant":[8],"advancement":[9],"in":[10,14],"technology":[11],"and":[12,35,81,116],"industry":[13],"recent":[15],"years.":[16],"training":[18,73],"these":[20],"largely":[22],"involves":[23],"human":[24,37,56,80,115],"feedback,":[25],"procedure":[27,104,125],"that":[28,122],"faces":[29],"challenges":[30],"including":[31],"intensive":[32],"resource":[33],"demands":[34],"subjective":[36],"preferences.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,101],"incorporate":[43],"feedback":[44,77],"provided":[45],"by":[46],"artificial":[47],"intelligence":[48],"(AI)":[49],"instead":[51],"relying":[53],"entirely":[54],"on":[55],"feedback.":[57],"We":[58,84],"propose":[59],"simulation":[61],"optimization":[62],"framework":[63],"to":[64,91,110],"train":[65],"the":[66,86,93,96,107,127,130],"model.":[68,132],"objective":[70,98],"function":[71],"for":[72,105],"is":[74],"approximated":[75,97],"using":[76],"from":[78,113],"both":[79,114],"AI":[82,117],"models.":[83,118],"employ":[85],"method":[87],"control":[89],"variate":[90],"reduce":[92],"variance":[94],"function.":[99],"Additionally,":[100],"provide":[102],"deciding":[106],"sample":[108],"size":[109],"acquire":[111],"preferences":[112],"Numerical":[119],"experiments":[120],"demonstrate":[121],"our":[123],"proposed":[124],"enhances":[126],"performance":[128]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}