{"id":"https://openalex.org/W4395022759","doi":"https://doi.org/10.1145/3626772.3657712","title":"Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs","display_name":"Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4395022759","doi":"https://doi.org/10.1145/3626772.3657712"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657712","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657712?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657712?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052291325","display_name":"Clemencia Siro","orcid":"https://orcid.org/0000-0001-5301-4244"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Clemencia Siro","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-5301-4244","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063466614","display_name":"Mohammad Aliannejadi","orcid":"https://orcid.org/0000-0002-9447-4172"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mohammad Aliannejadi","raw_affiliation_strings":["University of Amsterdam, Amstedam, Netherlands","of , The"],"raw_orcid":"https://orcid.org/0000-0002-9447-4172","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amstedam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"of , The","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands","of , The"],"raw_orcid":"https://orcid.org/0000-0002-1086-0202","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]},{"raw_affiliation_string":"of , The","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9811,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74983752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1952","last_page":"1962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9952999949455261,"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/T12128","display_name":"AI in Service Interactions","score":0.9944000244140625,"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":0.6411303281784058},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42730313539505005},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38864701986312866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6411303281784058},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42730313539505005},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38864701986312866}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3626772.3657712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657712","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657712?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/0789aae8-2f4d-4869-ad59-36c867b065e7","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/rethinking-the-evaluation-of-dialogue-systems-effects-of-user-feedback-on-crowdworkers-and-llms(0789aae8-2f4d-4869-ad59-36c867b065e7).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2404.12994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.12994","pdf_url":"https://arxiv.org/pdf/2404.12994","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,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/0789aae8-2f4d-4869-ad59-36c867b065e7","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/0789aae8-2f4d-4869-ad59-36c867b065e7","pdf_url":"https://pure.uva.nl/ws/files/244504658/3626772.3657712.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"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"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657712","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657712","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626772.3657712?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2289169492","display_name":"Fairness and Intersectional Non-Discrimination in Human Recommendation","funder_award_id":"101070212","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5550786340","display_name":"Hybrid Intelligence (HI): augmenting human intellect","funder_award_id":"024.004.022","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G6640760388","display_name":"Trustworthy AI-based Systems for Sustainable Growth","funder_award_id":"KICH3.LTP.20.006","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321008","display_name":"Universiteit van Amsterdam","ror":"https://ror.org/04dkp9463"},{"id":"https://openalex.org/F4320321014","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395022759.pdf","grobid_xml":"https://content.openalex.org/works/W4395022759.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1982204215","https://openalex.org/W2106576032","https://openalex.org/W2132232498","https://openalex.org/W2152184085","https://openalex.org/W2467445148","https://openalex.org/W2558888286","https://openalex.org/W2569307494","https://openalex.org/W2726137762","https://openalex.org/W2739567684","https://openalex.org/W2783668259","https://openalex.org/W2788085213","https://openalex.org/W2788493644","https://openalex.org/W2798435682","https://openalex.org/W2798782484","https://openalex.org/W2903257353","https://openalex.org/W2911638099","https://openalex.org/W2941486823","https://openalex.org/W2944069152","https://openalex.org/W2955157382","https://openalex.org/W2983435475","https://openalex.org/W2986224017","https://openalex.org/W2998679789","https://openalex.org/W3032777814","https://openalex.org/W3034491755","https://openalex.org/W3034808773","https://openalex.org/W3035734059","https://openalex.org/W3092103025","https://openalex.org/W3101366597","https://openalex.org/W3102132500","https://openalex.org/W3102862020","https://openalex.org/W3104405162","https://openalex.org/W3125913709","https://openalex.org/W3156287428","https://openalex.org/W4205737716","https://openalex.org/W4225000971","https://openalex.org/W4288080154","https://openalex.org/W4361193900","https://openalex.org/W4361807267","https://openalex.org/W4378942292","https://openalex.org/W4383605161","https://openalex.org/W4385571411","https://openalex.org/W4386928872"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0,12],"ad-hoc":[1],"retrieval,":[2],"evaluation":[3,31,36,61],"relies":[4,33],"heavily":[5],"on":[6,34,58,164,171],"user":[7,41,71,151,162,201,203,215],"actions,":[8],"including":[9],"implicit":[10],"feedback.":[11,193],"a":[13,49,83,135,179],"conversational":[14,50],"setting":[15],"such":[16],"signals":[17],"are":[18,158],"usually":[19],"unavailable":[20],"due":[21],"to":[22,116,161,169,178],"the":[23,26,30,60,79,98,146,190,212,223],"nature":[24],"of":[25,40,46,62,82,183,197,214],"interactions,":[27],"and,":[28],"instead,":[29],"often":[32],"crowdsourced":[35],"labels.":[37],"The":[38],"role":[39],"feedback":[42,152,163,176,204,216,227],"in":[43,48,138,145,195,217,229],"annotators'":[44],"assessment":[45,182],"turns":[47],"perception":[51],"has":[52],"been":[53],"little":[54],"studied.":[55],"We":[56,87,105],"focus":[57],"how":[59],"task-oriented":[63],"dialogue":[64],"systems":[65],"(TDSs),":[66],"is":[67,134],"affected":[68],"by":[69,141,185],"considering":[70],"feedback,":[72],"explicit":[73,192],"or":[74,199],"implicit,":[75],"as":[76,114],"provided":[77],"through":[78],"follow-up":[80,100],"utterance":[81,101],"turn":[84],"being":[85],"evaluated.":[86],"explore":[88],"and":[89,102,109,126,166,173,221],"compare":[90],"two":[91,147],"methodologies":[92],"for":[93,225],"assessing":[94],"TDSs:":[95],"one":[96,103],"includes":[97],"user's":[99,191],"without.":[104],"use":[106],"both":[107,142],"crowdworkers":[108],"large":[110],"language":[111],"models":[112],"(LLMs)":[113],"annotators":[115],"assess":[117],"system":[118,155,219],"responses":[119],"across":[120],"four":[121],"aspects:":[122],"relevance,":[123],"usefulness,":[124],"interestingness,":[125],"explanation":[127],"quality.":[128],"Our":[129],"findings":[130,210],"indicate":[131],"that":[132,150],"there":[133],"distinct":[136],"difference":[137],"ratings":[139],"assigned":[140],"annotator":[143],"groups":[144],"setups,":[148],"indicating":[149],"does":[153],"influence":[154],"evaluation.":[156],"Workers":[157],"more":[159,180],"susceptible":[160],"usefulness":[165,184],"interestingness":[167,172],"compared":[168],"LLMs":[170],"relevance.":[174],"User":[175],"leads":[177],"personalized":[181],"workers,":[186],"aligning":[187],"closely":[188],"with":[189],"Additionally,":[194],"cases":[196],"ambiguous":[198],"complex":[200],"requests,":[202],"improves":[205],"agreement":[206],"among":[207],"crowdworkers.":[208],"These":[209],"emphasize":[211],"significance":[213],"refining":[218],"evaluations":[220],"suggest":[222],"potential":[224],"automated":[226],"integration":[228],"future":[230],"research.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-04-23T00:00:00"}