{"id":"https://openalex.org/W7161278564","doi":"https://doi.org/10.1145/3805712.3808573","title":"A Standardized Re-evaluation of Conversational Recommender Systems on the ReDial Dataset","display_name":"A Standardized Re-evaluation of Conversational Recommender Systems on the ReDial Dataset","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7161278564","doi":"https://doi.org/10.1145/3805712.3808573"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808573","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808573","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 49th 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://doi.org/10.1145/3805712.3808573","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087083913","display_name":"Ivica Kostric","orcid":"https://orcid.org/0000-0002-0859-9762"},"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":"Ivica Kostric","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"raw_orcid":"https://orcid.org/0000-0002-0859-9762","affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136236782","display_name":"Krisztian Balog","orcid":null},"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":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I92008406"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2952","last_page":"2960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.5810999870300293,"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":0.5810999870300293,"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/T10028","display_name":"Topic Modeling","score":0.13369999825954437,"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":0.0843999981880188,"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/novelty","display_name":"Novelty","score":0.7368999719619751},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7055000066757202},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6319000124931335},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5343999862670898},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4366999864578247},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.35339999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692999839782715},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7368999719619751},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6319000124931335},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53329998254776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41620001196861267},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3808573","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808573","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.13053","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.13053","pdf_url":"https://arxiv.org/pdf/2605.13053","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808573","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808573","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6042694449424744}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"a":[4,104,173,181],"surge":[5],"of":[6,26,44,67,77,125,151],"research":[7],"into":[8],"conversational":[9,176],"recommender":[10],"systems":[11],"(CRS).":[12],"Among":[13],"existing":[14],"datasets,":[15],"ReDial":[16],"is":[17,34,111],"the":[18,32,42,65,68,75,149,152],"most":[19],"widely":[20],"used":[21,37],"benchmark,":[22],"cited":[23],"in":[24,30,38,41,135],"hundreds":[25],"studies.":[27,54],"However,":[28],"variations":[29],"how":[31],"dataset":[33],"preprocessed":[35],"and":[36,74,94,185,192],"experiments,":[39],"particularly":[40],"definition":[43],"ground-truth":[45],"items,":[46],"make":[47],"it":[48],"difficult":[49],"to":[50,114],"compare":[51],"results":[52],"across":[53,90],"These":[55],"comparisons":[56],"are":[57,133,144],"further":[58],"complicated":[59],"by":[60,148,156,161],"confounding":[61],"factors":[62],"such":[63],"as":[64],"choice":[66],"underlying":[69],"large":[70],"language":[71],"model":[72],"(LLM)":[73],"use":[76],"external":[78],"data":[79],"sources.":[80],"In":[81],"this":[82],"work,":[83],"we":[84,139,166],"revisit":[85],"seven":[86],"prominent":[87],"CRS":[88],"methods":[89],"three":[91],"architectural":[92,158],"families":[93],"evaluate":[95],"them":[96],"under":[97],"standardized":[98],"conditions.":[99],"Our":[100],"reproducibility":[101],"study":[102],"reveals":[103],"``granularity":[105],"gap,''":[106],"where":[107],"fine-grained":[108],"ranking":[109],"(Recall@1)":[110],"highly":[112],"sensitive":[113],"implementation":[115],"details,":[116],"while":[117],"our":[118],"replicability":[119],"analysis":[120],"shows":[121],"that":[122,132,141,168,189],"nearly":[123],"50%":[124],"reported":[126],"accuracy":[127],"stems":[128],"from":[129],"``repetition":[130],"shortcuts''":[131],"absent":[134],"novelty-focused":[136],"evaluation.":[137],"Furthermore,":[138],"find":[140],"performance":[142],"gains":[143],"often":[145],"driven":[146],"more":[147],"capacity":[150],"LLM":[153],"backbone":[154],"than":[155],"specific":[157],"innovations.":[159],"Finally,":[160],"applying":[162],"user-centric":[163],"utility":[164],"metrics,":[165],"demonstrate":[167],"traditional":[169],"recall":[170],"frequently":[171],"overstates":[172],"system's":[174],"actual":[175],"effectiveness.":[177],"This":[178],"work":[179],"establishes":[180],"transparent,":[182],"controlled":[183],"baseline":[184],"promotes":[186],"evaluation":[187],"practices":[188],"prioritize":[190],"novelty":[191],"interaction":[193],"efficiency.":[194]},"counts_by_year":[],"updated_date":"2026-07-16T06:00:37.324182","created_date":"2026-05-16T00:00:00"}