{"id":"https://openalex.org/W4393399744","doi":"https://doi.org/10.48550/arxiv.2403.20194","title":"ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models","display_name":"ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models","publication_year":2024,"publication_date":"2024-03-29","ids":{"openalex":"https://openalex.org/W4393399744","doi":"https://doi.org/10.48550/arxiv.2403.20194"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.20194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.20194","pdf_url":"https://arxiv.org/pdf/2403.20194","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.20194","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100435103","display_name":"Shuo Liu","orcid":"https://orcid.org/0000-0002-3092-7638"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Shuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090152810","display_name":"Kaining Ying","orcid":"https://orcid.org/0000-0003-2596-1847"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying, Kaining","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396897","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-3572-7053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101146108","display_name":"Yue Yang","orcid":"https://orcid.org/0000-0002-3092-383X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497048","display_name":"Yuqi Lin","orcid":"https://orcid.org/0000-0002-3019-5684"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yuqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074422885","display_name":"Tianle Zhang","orcid":"https://orcid.org/0000-0002-0779-5905"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tianle","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057986563","display_name":"Chuanhao Li","orcid":"https://orcid.org/0009-0006-2440-0596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chuanhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752686","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6685-7950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Ping","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827257","display_name":"Wenqi Shao","orcid":"https://orcid.org/0000-0003-3781-4086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Wenqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036606244","display_name":"Kaipeng Zhang","orcid":"https://orcid.org/0000-0001-6105-6532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaipeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5100435103"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9980999827384949,"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":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9580000042915344,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9153000116348267,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.906524658203125},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.736653208732605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6365980505943298},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.5409387946128845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4112909734249115},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37817513942718506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3307088613510132},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2327651083469391},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.21294018626213074},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0879325270652771},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07602715492248535}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.906524658203125},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.736653208732605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365980505943298},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.5409387946128845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4112909734249115},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37817513942718506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3307088613510132},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2327651083469391},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.21294018626213074},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0879325270652771},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07602715492248535}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.20194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.20194","pdf_url":"https://arxiv.org/pdf/2403.20194","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.20194","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.20194","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.20194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.20194","pdf_url":"https://arxiv.org/pdf/2403.20194","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393399744.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2228992124","https://openalex.org/W2613954729","https://openalex.org/W3130118443","https://openalex.org/W1955947659","https://openalex.org/W2759378137","https://openalex.org/W2376974064","https://openalex.org/W3188579947","https://openalex.org/W4289529495","https://openalex.org/W4386695291","https://openalex.org/W2355699586"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"ConvBench,":[3],"a":[4,28,48,109,139],"novel":[5],"multi-turn":[6,71,121],"conversation":[7,90,101],"evaluation":[8],"benchmark":[9],"tailored":[10],"for":[11,141],"Large":[12],"Vision-Language":[13],"Models":[14],"(LVLMs).":[15],"Unlike":[16],"existing":[17],"benchmarks":[18],"that":[19],"assess":[20],"individual":[21],"capabilities":[22],"in":[23,120,127],"single-turn":[24],"dialogues,":[25],"ConvBench":[26,66,96,136],"adopts":[27],"three-level":[29],"multimodal":[30],"capability":[31,94],"hierarchy,":[32,95],"mimicking":[33],"human":[34,118],"cognitive":[35,53],"processes":[36],"by":[37],"stacking":[38],"up":[39],"perception,":[40],"reasoning,":[41],"and":[42,61,88,117,133],"creativity.":[43,65],"Each":[44],"level":[45],"focuses":[46],"on":[47],"distinct":[49],"capability,":[50],"mirroring":[51],"the":[52,93],"progression":[54],"from":[55],"basic":[56],"perception":[57,126],"to":[58,63,103,131],"logical":[59],"reasoning":[60,132],"ultimately":[62],"advanced":[64],"comprises":[67],"577":[68],"meticulously":[69],"curated":[70],"conversations":[72],"encompassing":[73],"215":[74],"tasks":[75],"reflective":[76],"of":[77,100],"real-world":[78],"demands.":[79],"Automatic":[80],"evaluations":[81],"quantify":[82],"response":[83],"performance":[84,110,119],"at":[85,145],"each":[86],"turn":[87],"overall":[89],"level.":[91],"Leveraging":[92],"enables":[97],"precise":[98],"attribution":[99],"mistakes":[102],"specific":[104],"levels.":[105],"Experimental":[106],"results":[107],"reveal":[108],"gap":[111],"between":[112],"multi-modal":[113,128],"models,":[114],"including":[115],"GPT4-V,":[116],"conversations.":[122],"Additionally,":[123],"weak":[124],"fine-grained":[125],"models":[129],"contributes":[130],"creation":[134],"failures.":[135],"serves":[137],"as":[138],"catalyst":[140],"further":[142],"research":[143],"aimed":[144],"enhancing":[146],"visual":[147],"dialogues.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2024-04-02T00:00:00"}