{"id":"https://openalex.org/W4391116977","doi":"https://doi.org/10.1609/aaaiss.v2i1.27668","title":"Clarifying the Dialogue-Level Performance of GPT-3.5 and GPT-4 in Task-Oriented and Non-Task-Oriented Dialogue Systems","display_name":"Clarifying the Dialogue-Level Performance of GPT-3.5 and GPT-4 in Task-Oriented and Non-Task-Oriented Dialogue Systems","publication_year":2024,"publication_date":"2024-01-22","ids":{"openalex":"https://openalex.org/W4391116977","doi":"https://doi.org/10.1609/aaaiss.v2i1.27668"},"language":"en","primary_location":{"id":"doi:10.1609/aaaiss.v2i1.27668","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v2i1.27668","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27668/27441","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27668/27441","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110597620","display_name":"Shinya Iizuka","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinya Iizuka","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017829312","display_name":"Shota Mochizuki","orcid":"https://orcid.org/0009-0007-4092-8734"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Mochizuki","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049970310","display_name":"Atsumoto Ohashi","orcid":"https://orcid.org/0009-0004-0990-7255"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsumoto Ohashi","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101716048","display_name":"Sanae Yamashita","orcid":"https://orcid.org/0009-0002-5994-4703"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sanae Yamashita","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016969134","display_name":"Ao Guo","orcid":"https://orcid.org/0000-0001-8631-5457"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ao Guo","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004045909","display_name":"Ryuichiro Higashinaka","orcid":"https://orcid.org/0000-0002-6994-3977"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichiro Higashinaka","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.7704,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85688081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"2","issue":"1","first_page":"182","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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/T12031","display_name":"Speech and dialogue systems","score":0.9905999898910522,"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":0.9905999898910522,"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/utterance","display_name":"Utterance","score":0.8146104216575623},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7604050636291504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7313292026519775},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6178848743438721},{"id":"https://openalex.org/keywords/persona","display_name":"Persona","score":0.5524272322654724},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.48846665024757385},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4878104031085968},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.466008722782135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4164503514766693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33939921855926514},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2764344811439514},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06599929928779602}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8146104216575623},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7604050636291504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313292026519775},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6178848743438721},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.5524272322654724},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.48846665024757385},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4878104031085968},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.466008722782135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4164503514766693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33939921855926514},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2764344811439514},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06599929928779602},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaaiss.v2i1.27668","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v2i1.27668","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27668/27441","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaaiss.v2i1.27668","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaaiss.v2i1.27668","pdf_url":"https://ojs.aaai.org/index.php/AAAI-SS/article/download/27668/27441","source":{"id":"https://openalex.org/S4389157828","display_name":"Proceedings of the AAAI Symposium Series","issn_l":"2994-4317","issn":["2994-4317"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Symposium Series","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G556986091","display_name":null,"funder_award_id":"JP-MJMS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391116977.pdf","grobid_xml":"https://content.openalex.org/works/W4391116977.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1983382331","https://openalex.org/W2071559616","https://openalex.org/W2891732163","https://openalex.org/W2898875342","https://openalex.org/W2900035924","https://openalex.org/W2917128112","https://openalex.org/W2924343356","https://openalex.org/W2950242852","https://openalex.org/W2951583236","https://openalex.org/W2952607215","https://openalex.org/W2962965441","https://openalex.org/W2963825865","https://openalex.org/W2964006684","https://openalex.org/W2964352131","https://openalex.org/W2971351151","https://openalex.org/W2981852735","https://openalex.org/W3005912270","https://openalex.org/W3034424015","https://openalex.org/W3036394672","https://openalex.org/W3037879762","https://openalex.org/W3161857679","https://openalex.org/W3168867926","https://openalex.org/W3201566090","https://openalex.org/W4224912544","https://openalex.org/W4231760770","https://openalex.org/W4288089799","https://openalex.org/W4319793302","https://openalex.org/W4319862409","https://openalex.org/W4327810158","https://openalex.org/W4360836968","https://openalex.org/W4366559955","https://openalex.org/W4372272550","https://openalex.org/W4385572445","https://openalex.org/W4389010465","https://openalex.org/W6639660458","https://openalex.org/W6646139809","https://openalex.org/W6698480918"],"related_works":["https://openalex.org/W2795366572","https://openalex.org/W2886588594","https://openalex.org/W3005214328","https://openalex.org/W2920961600","https://openalex.org/W3091061106","https://openalex.org/W4312802148","https://openalex.org/W2610743940","https://openalex.org/W4285553851","https://openalex.org/W4389400787","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Although":[0],"large":[1],"language":[2,16],"models":[3],"such":[4],"as":[5],"ChatGPT":[6],"and":[7,61,66,79,96],"GPT-4":[8,62,87],"have":[9],"achieved":[10],"superb":[11],"performances":[12],"in":[13,51,70,77,110],"various":[14],"natural":[15],"processing":[17],"tasks,":[18],"their":[19,74],"dialogue":[20,81],"performance":[21,76,101],"is":[22,30,45,54],"sometimes":[23],"not":[24],"very":[25],"clear":[26],"because":[27],"the":[28,34,38,46],"evaluation":[29,47],"often":[31],"done":[32],"on":[33,108],"utterance":[35,42],"level":[36],"where":[37],"quality":[39],"of":[40,59],"an":[41],"given":[43],"context":[44],"target.":[48],"Our":[49,83],"objective":[50],"this":[52],"work":[53],"to":[55,63,72,102],"conduct":[56],"human":[57],"evaluations":[58],"GPT-3.5":[60],"perform":[64],"MultiWOZ":[65],"persona-based":[67,111],"chat":[68],"tasks":[69],"order":[71],"verify":[73],"dialogue-level":[75],"task-oriented":[78],"non-task-oriented":[80],"systems.":[82],"findings":[84],"show":[85],"that":[86],"performs":[88],"comparably":[89],"with":[90],"a":[91,98],"carefully":[92],"created":[93],"rule-based":[94],"system":[95],"has":[97],"significantly":[99],"superior":[100],"other":[103],"systems,":[104],"including":[105],"those":[106],"based":[107],"GPT-3.5,":[109],"chat.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}