{"id":"https://openalex.org/W7163031260","doi":"https://doi.org/10.1145/3774935.3806172","title":"Can Third-Party Annotators Reliably Evaluate Conversational Recommender Systems?","display_name":"Can Third-Party Annotators Reliably Evaluate Conversational Recommender Systems?","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163031260","doi":"https://doi.org/10.1145/3774935.3806172"},"language":null,"primary_location":{"id":"doi:10.1145/3774935.3806172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3806172","pdf_url":null,"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 34th ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774935.3806172","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063771897","display_name":"Michael M\u00fcller","orcid":"https://orcid.org/0009-0005-0918-8833"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael M\u00fcller","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0009-0005-0918-8833","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086678250","display_name":"Amir Reza Mohammadi","orcid":"https://orcid.org/0000-0003-3934-6941"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Amir Reza Mohammadi","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0000-0003-3934-6941","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084204756","display_name":"Andreas Peintner","orcid":"https://orcid.org/0000-0001-7337-524X"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andreas Peintner","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0000-0001-7337-524X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126489104","display_name":"Beatriz Barroso Gstrein","orcid":null},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Beatriz Barroso Gstrein","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0009-0006-9111-5402","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073412960","display_name":"G\u00fcnther Specht","orcid":"https://orcid.org/0000-0003-0978-7201"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"G\u00fcnther Specht","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0978-7201","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070525687","display_name":"Eva Zangerle","orcid":"https://orcid.org/0000-0003-3195-8273"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Eva Zangerle","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0000-0003-3195-8273","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I190249584"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"351","last_page":"355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.41749998927116394,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.41749998927116394,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.14509999752044678,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.13199999928474426,"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/reliability","display_name":"Reliability (semiconductor)","score":0.7465000152587891},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5394999980926514},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.44920000433921814},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.44850000739097595},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41929998993873596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775999903678894},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7465000152587891},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521399974822998},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3603000044822693},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774935.3806172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3806172","pdf_url":null,"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 34th ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774935.3806172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774935.3806172","pdf_url":null,"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 34th ACM Conference on User Modeling, Adaptation and Personalization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2067724039","https://openalex.org/W2124381750","https://openalex.org/W2141766660","https://openalex.org/W2162111811","https://openalex.org/W2327037637","https://openalex.org/W3014901735","https://openalex.org/W4234180827","https://openalex.org/W4285091076","https://openalex.org/W4388210288","https://openalex.org/W4394007331","https://openalex.org/W4396712844","https://openalex.org/W4399913292","https://openalex.org/W4403221076","https://openalex.org/W4406548969","https://openalex.org/W4409749882","https://openalex.org/W4414034937","https://openalex.org/W4414977905","https://openalex.org/W6891563327","https://openalex.org/W6948330358"],"related_works":[],"abstract_inverted_index":{"User-centric":[0],"evaluation":[1,72,170],"has":[2],"become":[3],"a":[4,60,148,154],"key":[5],"paradigm":[6],"for":[7,176],"assessing":[8],"Conversational":[9],"Recommender":[10],"Systems":[11],"(CRS),":[12],"aiming":[13],"to":[14],"capture":[15],"subjective":[16],"qualities":[17],"such":[18,119,134],"as":[19,120,135],"satisfaction,":[20],"trust,":[21],"and":[22,67,98,108,116,123,137,168,172,179],"rapport.":[23],"To":[24],"enable":[25],"scalable":[26],"evaluation,":[27],"recent":[28],"work":[29],"increasingly":[30],"relies":[31],"on":[32,73,85],"third-party":[33,159],"annotations":[34,80],"of":[35,49,69,105,166],"static":[36,74],"dialogue":[37,75],"logs":[38],"by":[39],"crowd":[40,83],"workers":[41,84],"or":[42],"large":[43],"language":[44],"models.":[45],"However,":[46],"the":[47,65,90,103,164,174],"reliability":[48,66,96,127],"this":[50,56],"practice":[51],"remains":[52],"largely":[53],"unexamined.":[54],"In":[55],"paper,":[57],"we":[58,101],"present":[59],"large-scale":[61],"empirical":[62],"study":[63],"investigating":[64],"structure":[68],"user-centric":[70],"CRS":[71,184],"transcripts.":[76],"We":[77],"collected":[78],"1,053":[79],"from":[81],"124":[82],"200":[86],"ReDial":[87],"dialogues":[88],"using":[89],"18-dimensional":[91],"CRS-Que":[92],"framework.":[93],"Using":[94],"random-effects":[95],"models":[97],"correlation":[99],"analysis,":[100],"quantify":[102],"stability":[104],"individual":[106],"dimensions":[107,118,145],"their":[109],"interdependencies.":[110],"Our":[111],"results":[112],"show":[113],"that":[114],"utilitarian":[115],"outcome-oriented":[117],"accuracy,":[121],"usefulness,":[122],"satisfaction":[124],"achieve":[125],"moderate":[126],"under":[128],"aggregation,":[129],"whereas":[130],"socially":[131],"grounded":[132],"constructs":[133],"humanness":[136],"rapport":[138],"are":[139],"substantially":[140],"less":[141],"reliable.":[142],"Furthermore,":[143],"many":[144],"collapse":[146],"into":[147],"single":[149],"global":[150],"quality":[151],"signal,":[152],"revealing":[153],"strong":[155],"halo":[156],"effect":[157],"in":[158,182],"judgments.":[160],"These":[161],"findings":[162],"challenge":[163],"validity":[165],"single-annotator":[167],"LLM-based":[169],"protocols":[171],"motivate":[173],"need":[175],"multi-rater":[177],"aggregation":[178],"dimension":[180],"reduction":[181],"offline":[183],"evaluation.":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-02T00:00:00"}