{"id":"https://openalex.org/W4414977905","doi":"https://doi.org/10.1145/3767695.3769478","title":"Limitations of Current Evaluation Practices for Conversational Recommender Systems and the Potential of User Simulation","display_name":"Limitations of Current Evaluation Practices for Conversational Recommender Systems and the Potential of User Simulation","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4414977905","doi":"https://doi.org/10.1145/3767695.3769478"},"language":"en","primary_location":{"id":"doi:10.1145/3767695.3769478","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769478","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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767695.3769478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020641281","display_name":"Nolwenn Bernard","orcid":"https://orcid.org/0009-0007-0565-3210"},"institutions":[{"id":"https://openalex.org/I102520234","display_name":"TH K\u00f6ln - University of Applied Sciences","ror":"https://ror.org/014nnvj65","country_code":"DE","type":"education","lineage":["https://openalex.org/I102520234"]},{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["DE","NO"],"is_corresponding":false,"raw_author_name":"Nolwenn Bernard","raw_affiliation_strings":["TH K\u00f6ln, Cologne, Germany and University of Stavanger, Stavanger, Norway"],"raw_orcid":"https://orcid.org/0009-0007-0565-3210","affiliations":[{"raw_affiliation_string":"TH K\u00f6ln, Cologne, Germany and University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406","https://openalex.org/I102520234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059926999","display_name":"Krisztian Balog","orcid":"https://orcid.org/0000-0003-2762-721X"},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Krisztian Balog","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"raw_orcid":"https://orcid.org/0000-0003-2762-721X","affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9193999767303467,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9193999767303467,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9129999876022339,"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/recommender-system","display_name":"Recommender system","score":0.6758999824523926},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.531499981880188},{"id":"https://openalex.org/keywords/user-experience-design","display_name":"User experience design","score":0.4607999920845032},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.4602999985218048},{"id":"https://openalex.org/keywords/user-satisfaction","display_name":"User satisfaction","score":0.4205000102519989},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.37290000915527344},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3668000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057000041007996},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6758999824523926},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5727999806404114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.4602999985218048},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.430400013923645},{"id":"https://openalex.org/C3017893058","wikidata":"https://www.wikidata.org/wiki/Q999278","display_name":"User satisfaction","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3075000047683716},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C63880386","wikidata":"https://www.wikidata.org/wiki/Q5157592","display_name":"Computer user satisfaction","level":4,"score":0.2890999913215637},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2986148714","wikidata":"https://www.wikidata.org/wiki/Q7300799","display_name":"Interactive simulation","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C80519477","wikidata":"https://www.wikidata.org/wiki/Q3532236","display_name":"Scenario testing","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3767695.3769478","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769478","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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.05624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.05624","pdf_url":"https://arxiv.org/pdf/2510.05624","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3767695.3769478","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769478","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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2589906563","display_name":null,"funder_award_id":"309834","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Research":[0],"and":[1,12,36,47,67,76,138,171,177],"development":[2],"on":[3,10,43,113],"conversational":[4],"recommender":[5],"systems":[6,22],"(CRSs)":[7],"critically":[8,31],"depends":[9],"sound":[11],"reliable":[13],"evaluation":[14,34,52,110,178],"methodologies.":[15],"However,":[16],"the":[17,41,48,90],"interactive":[18],"nature":[19],"of":[20,50,92,128],"these":[21,85,154],"poses":[23],"significant":[24,158],"challenges":[25],"for":[26,168],"automatic":[27],"evaluation.":[28,152],"This":[29],"paper":[30],"examines":[32],"current":[33],"practices":[35],"identifies":[37],"two":[38],"key":[39],"limitations:":[40],"over-reliance":[42],"static":[44,104],"test":[45],"collections":[46],"inadequacy":[49],"existing":[51,65],"metrics.":[53,179],"To":[54,83],"substantiate":[55],"this":[56,87],"critique,":[57],"we":[58,107,164],"analyze":[59],"real":[60,123],"user":[61,74,93,124],"interactions":[62],"with":[63,122,146],"nine":[64],"CRSs":[66],"demonstrate":[68],"a":[69,101,114,157],"striking":[70],"disconnect":[71],"between":[72],"self-reported":[73],"satisfaction":[75],"performance":[77],"scores":[78],"reported":[79],"in":[80,161,173],"prior":[81],"literature.":[82],"address":[84],"limitations,":[86],"work":[88],"explores":[89],"potential":[91],"simulation":[94,130,175],"to":[95,119,150],"generate":[96],"dynamic":[97],"interaction":[98],"data,":[99],"offering":[100],"departure":[102],"from":[103],"datasets.":[105],"Furthermore,":[106],"propose":[108],"novel":[109],"metrics,":[111],"based":[112],"general":[115],"reward/cost":[116],"framework,":[117],"designed":[118],"better":[120],"align":[121],"satisfaction.":[125],"Our":[126],"analysis":[127],"different":[129],"approaches":[131],"provides":[132],"valuable":[133],"insights":[134],"into":[135],"their":[136],"effectiveness":[137],"reveals":[139],"promising":[140],"initial":[141],"results,":[142],"showing":[143],"improved":[144],"correlation":[145],"system":[147],"rankings":[148],"compared":[149],"human":[151],"While":[153],"findings":[155],"indicate":[156],"step":[159],"forward":[160],"CRS":[162],"evaluation,":[163],"also":[165],"identify":[166],"areas":[167],"future":[169],"research":[170],"refinement":[172],"both":[174],"techniques":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
