{"id":"https://openalex.org/W4389523709","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.148","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","display_name":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389523709","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.148"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.148","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.148","pdf_url":"https://aclanthology.org/2023.emnlp-main.148.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.emnlp-main.148.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051050719","display_name":"Hannah Rose Kirk","orcid":"https://orcid.org/0000-0002-7419-5993","observed_orcids":["https://orcid.org/0000-0002-7419-5993"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hannah Kirk","raw_affiliation_strings":["University of Oxford,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081572871","display_name":"Andrew Bean","orcid":"https://orcid.org/0000-0002-4541-9759","observed_orcids":["https://orcid.org/0000-0002-4541-9759"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Bean","raw_affiliation_strings":["University of Oxford,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084936290","display_name":"Bertie Vidgen","orcid":"https://orcid.org/0000-0002-7892-0814","observed_orcids":["https://orcid.org/0000-0002-7892-0814"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bertie Vidgen","raw_affiliation_strings":["University of Oxford,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050023117","display_name":"Paul R\u00f6ttger","orcid":"https://orcid.org/0009-0008-7115-6893","observed_orcids":["https://orcid.org/0009-0008-7115-6893"]},"institutions":[{"id":"https://openalex.org/I71209653","display_name":"Bocconi University","ror":"https://ror.org/05crjpb27","country_code":"IT","type":"education","lineage":["https://openalex.org/I71209653"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paul Rottger","raw_affiliation_strings":["Bocconi University , 3 Meedan","Bocconi University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bocconi University , 3 Meedan","institution_ids":["https://openalex.org/I71209653"]},{"raw_affiliation_string":"Bocconi University,","institution_ids":["https://openalex.org/I71209653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029882049","display_name":"Scott A. Hale","orcid":"https://orcid.org/0000-0002-6894-4951","observed_orcids":["https://orcid.org/0000-0002-6894-4951"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Scott Hale","raw_affiliation_strings":["University of Oxford,","Meedan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford,","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Meedan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051050719"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":3.2491,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93434783,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2409","last_page":"2430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.23520000278949738,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.23520000278949738,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.20890000462532043,"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":0.16820000112056732,"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/human-feedback","display_name":"human feedback","score":0.6809999942779541},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9589999914169312},{"id":"https://openalex.org/keywords/preference-learning","display_name":"preference learning","score":0.6499999761581421},{"id":"https://openalex.org/keywords/value-alignment","display_name":"value alignment","score":0.5419999957084656},{"id":"https://openalex.org/keywords/feedback-collection","display_name":"feedback collection","score":0.8299999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485047936439514},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.4101041555404663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3316057324409485},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09926983714103699},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.148","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.148","pdf_url":"https://aclanthology.org/2023.emnlp-main.148.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.07629","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.07629","pdf_url":"https://arxiv.org/pdf/2310.07629","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:iris.unibocconi.it:11565/4071565","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/11565/4071565","pdf_url":null,"source":{"id":"https://openalex.org/S7407055170","display_name":"Archivio istituzionale della Ricerca - Bocconi","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2310.07629","doi":"https://doi.org/10.48550/arxiv.2310.07629","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.07629","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.148","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.148","pdf_url":"https://aclanthology.org/2023.emnlp-main.148.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4489679334","display_name":null,"funder_award_id":"ES/P000649/","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G4605265282","display_name":null,"funder_award_id":"P000649","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G6530115474","display_name":"Incorporating Demographic Factors into Natural Language Processing Models","funder_award_id":"949944","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G8707773525","display_name":"Grand Union Doctoral Training Partnership","funder_award_id":"ES/P000649/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"},{"id":"https://openalex.org/F4320336183","display_name":"Clarendon Fund","ror":null},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389523709.pdf","grobid_xml":"https://content.openalex.org/works/W4389523709.grobid-xml"},"referenced_works_count":143,"referenced_works":["https://openalex.org/W1774659654","https://openalex.org/W1962580118","https://openalex.org/W1994785817","https://openalex.org/W2034637506","https://openalex.org/W2064675550","https://openalex.org/W2104227891","https://openalex.org/W2125016606","https://openalex.org/W2132007419","https://openalex.org/W2250969425","https://openalex.org/W2251180427","https://openalex.org/W2251709151","https://openalex.org/W2539350388","https://openalex.org/W2559038528","https://openalex.org/W2575124246","https://openalex.org/W2579486552","https://openalex.org/W2609616693","https://openalex.org/W2626778328","https://openalex.org/W2626804490","https://openalex.org/W2735574368","https://openalex.org/W2737114849","https://openalex.org/W2739515658","https://openalex.org/W2739752763","https://openalex.org/W2741325996","https://openalex.org/W2773181053","https://openalex.org/W2787403940","https://openalex.org/W2787560479","https://openalex.org/W2798299685","https://openalex.org/W2799082722","https://openalex.org/W2896457183","https://openalex.org/W2898637828","https://openalex.org/W2910458567","https://openalex.org/W2911227954","https://openalex.org/W2936262349","https://openalex.org/W2946291122","https://openalex.org/W2950242852","https://openalex.org/W2953522645","https://openalex.org/W2953981431","https://openalex.org/W2958608582","https://openalex.org/W2963068985","https://openalex.org/W2963119657","https://openalex.org/W2963167310","https://openalex.org/W2963228265","https://openalex.org/W2963560082","https://openalex.org/W2963567240","https://openalex.org/W2963825865","https://openalex.org/W2965568842","https://openalex.org/W2969117066","https://openalex.org/W2969282158","https://openalex.org/W2970990259","https://openalex.org/W2971032890","https://openalex.org/W2973379954","https://openalex.org/W2984662393","https://openalex.org/W2992807692","https://openalex.org/W2996314454","https://openalex.org/W2997607995","https://openalex.org/W3008655042","https://openalex.org/W3019416653","https://openalex.org/W3024029620","https://openalex.org/W3034418628","https://openalex.org/W3043104149","https://openalex.org/W3047185145","https://openalex.org/W3052814785","https://openalex.org/W3082115681","https://openalex.org/W3088599783","https://openalex.org/W3092995464","https://openalex.org/W3093233911","https://openalex.org/W3094997972","https://openalex.org/W3098258760","https://openalex.org/W3098467034","https://openalex.org/W3099072156","https://openalex.org/W3125444967","https://openalex.org/W3158733382","https://openalex.org/W3168771811","https://openalex.org/W3171850892","https://openalex.org/W3174090807","https://openalex.org/W3174256071","https://openalex.org/W3175060421","https://openalex.org/W3176618728","https://openalex.org/W3184144760","https://openalex.org/W3188785232","https://openalex.org/W3199147803","https://openalex.org/W3199369541","https://openalex.org/W3200980294","https://openalex.org/W3201174429","https://openalex.org/W3202173763","https://openalex.org/W3206428286","https://openalex.org/W3206621920","https://openalex.org/W3215698779","https://openalex.org/W4200635105","https://openalex.org/W4200635688","https://openalex.org/W4221103197","https://openalex.org/W4221164017","https://openalex.org/W4223477065","https://openalex.org/W4223908421","https://openalex.org/W4224294371","https://openalex.org/W4224866872","https://openalex.org/W4225006216","https://openalex.org/W4225134894","https://openalex.org/W4226227340","https://openalex.org/W4226278401","https://openalex.org/W4226399820","https://openalex.org/W4281392527","https://openalex.org/W4285217123","https://openalex.org/W4285295903","https://openalex.org/W4285484119","https://openalex.org/W4287854995","https://openalex.org/W4288431687","https://openalex.org/W4296405185","https://openalex.org/W4296413526","https://openalex.org/W4298181573","https://openalex.org/W4299830158","https://openalex.org/W4300206276","https://openalex.org/W4306706478","https://openalex.org/W4308615640","https://openalex.org/W4309674289","https://openalex.org/W4311991106","https://openalex.org/W4312050653","https://openalex.org/W4312091576","https://openalex.org/W4312091890","https://openalex.org/W4319453300","https://openalex.org/W4321392329","https://openalex.org/W4323929307","https://openalex.org/W4362514994","https://openalex.org/W4365211596","https://openalex.org/W4366196653","https://openalex.org/W4378718328","https://openalex.org/W4378771755","https://openalex.org/W4379474731","https://openalex.org/W4385570984","https://openalex.org/W4385571710","https://openalex.org/W4385571841","https://openalex.org/W4385574250","https://openalex.org/W4385734243","https://openalex.org/W4387223260","https://openalex.org/W4387389810","https://openalex.org/W4393160410","https://openalex.org/W4404752327","https://openalex.org/W6913077474","https://openalex.org/W7131862832","https://openalex.org/W7133189643","https://openalex.org/W7133206970","https://openalex.org/W7133223423","https://openalex.org/W7133238093"],"related_works":["https://openalex.org/W4399835902","https://openalex.org/W7047956794","https://openalex.org/W4387892197","https://openalex.org/W4416723396","https://openalex.org/W7109151420","https://openalex.org/W4387223260","https://openalex.org/W4319453300","https://openalex.org/W7202047765","https://openalex.org/W4404782792","https://openalex.org/W4415850505"],"abstract_inverted_index":{"Human":[0],"feedback":[1,22,71,101,113],"is":[2,15,27,102],"increasingly":[3],"used":[4],"to":[5,18],"steer":[6],"the":[7,57,64,87],"behaviours":[8],"of":[9,79,112],"Large":[10],"Language":[11],"Models":[12],"(LLMs).However,":[13],"it":[14],"unclear":[16],"how":[17,100],"collect":[19],"and":[20,30,38,59,82,97,99,104,122],"incorporate":[21],"in":[23,115],"a":[24,109],"way":[25],"that":[26],"efficient,":[28],"effective":[29],"unbiased,":[31],"especially":[32],"for":[33,46,68,89,94],"highly":[34],"subjective":[35],"human":[36,49,70],"preferences":[37],"values.In":[39],"this":[40],"paper,":[41],"we":[42,62,75,107],"survey":[43],"existing":[44],"approaches":[45],"learning":[47,114],"from":[48,56,105],"feedback,":[50],"drawing":[51],"on":[52],"95":[53],"papers":[54],"primarily":[55],"ACL":[58],"arXiv":[60],"repositories.First,":[61],"summarise":[63],"past,":[65],"pre-LLM":[66],"trends":[67],"integrating":[69],"into":[72],"language":[73],"models.Second,":[74],"give":[76],"an":[77],"overview":[78],"present":[80],"techniques":[81],"practices,":[83],"as":[84,86],"well":[85],"motivations":[88],"using":[90],"feedback;":[91],"conceptual":[92,121],"frameworks":[93],"defining":[95],"values":[96],"preferences;":[98],"collected":[103],"whom.Finally,":[106],"encourage":[108],"better":[110],"future":[111],"LLMs":[116],"by":[117],"raising":[118],"five":[119],"unresolved":[120],"practical":[123],"challenges.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-12-11T00:00:00"}