{"id":"https://openalex.org/W4403565106","doi":"https://doi.org/10.48550/arxiv.2410.09421","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","display_name":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","publication_year":2024,"publication_date":"2024-10-12","ids":{"openalex":"https://openalex.org/W4403565106","doi":"https://doi.org/10.48550/arxiv.2410.09421"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.09421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09421","pdf_url":"https://arxiv.org/pdf/2410.09421","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.09421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100440326","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-5374-7293"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021667482","display_name":"Zhihui Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Zhihui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004617059","display_name":"Mukai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mukai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041945106","display_name":"Shunian Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shunian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058808692","display_name":"Peiyi Wang","orcid":"https://orcid.org/0000-0002-9904-0664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Peiyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115590703","display_name":"Liang Chen","orcid":"https://orcid.org/0009-0005-2899-8997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Liang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063920160","display_name":"Yazheng Yang","orcid":"https://orcid.org/0000-0003-1627-8341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yazheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084990114","display_name":"Benyou Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Benyou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014554970","display_name":"Lingpeng Kong","orcid":"https://orcid.org/0000-0002-9033-2724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Lingpeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100453144","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-5378-6404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100440326"],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.917900025844574,"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/scale","display_name":"Scale (ratio)","score":0.6310171484947205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6278117299079895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.50276780128479},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41196495294570923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3331137001514435},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.1565796136856079},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1348462998867035}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6310171484947205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6278117299079895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50276780128479},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41196495294570923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3331137001514435},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1565796136856079},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1348462998867035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.09421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09421","pdf_url":"https://arxiv.org/pdf/2410.09421","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.09421","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.09421","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.09421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09421","pdf_url":"https://arxiv.org/pdf/2410.09421","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403565106.pdf","grobid_xml":"https://content.openalex.org/works/W4403565106.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"As":[0],"large":[1],"vision-language":[2,56,82],"models":[3,17,70,157],"(LVLMs)":[4],"evolve":[5],"rapidly,":[6],"the":[7,22,39,53,76,137],"demand":[8],"for":[9,47,81],"high-quality":[10],"and":[11,32,64,104,114,118,126,156],"diverse":[12],"data":[13,26],"to":[14,44,147],"align":[15],"these":[16],"becomes":[18],"increasingly":[19],"crucial.":[20],"However,":[21],"creation":[23],"of":[24,41,78,139],"such":[25],"with":[27],"human":[28,72],"supervision":[29,46],"proves":[30],"costly":[31],"time-intensive.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,84],"investigate":[38],"efficacy":[40],"AI":[42,79,140],"feedback":[43,57,80],"scale":[45],"aligning":[48],"LVLMs.":[49],"We":[50],"introduce":[51],"VLFeedback,":[52],"first":[54],"large-scale":[55],"dataset,":[58,153],"comprising":[59],"over":[60],"82K":[61],"multi-modal":[62],"instructions":[63],"comprehensive":[65,150],"rationales":[66],"generated":[67],"by":[68,112],"off-the-shelf":[69],"without":[71],"annotations.":[73],"To":[74],"evaluate":[75],"effectiveness":[77],"alignment,":[83],"train":[85],"Silkie,":[86],"an":[87],"LVLM":[88],"fine-tuned":[89],"via":[90],"direct":[91],"preference":[92,145],"optimization":[93],"on":[94,124],"VLFeedback.":[95],"Silkie":[96],"showcases":[97],"exceptional":[98],"performance":[99],"regarding":[100],"helpfulness,":[101],"visual":[102],"faithfulness,":[103],"safety":[105],"metrics.":[106],"It":[107],"outperforms":[108],"its":[109],"base":[110],"model":[111],"6.9\\%":[113],"9.5\\%":[115],"in":[116,143],"perception":[117],"cognition":[119],"tasks,":[120],"reduces":[121],"hallucination":[122],"issues":[123],"MMHal-Bench,":[125],"exhibits":[127],"enhanced":[128],"resilience":[129],"against":[130],"red-teaming":[131],"attacks.":[132],"Furthermore,":[133],"our":[134],"analysis":[135],"underscores":[136],"advantage":[138],"feedback,":[141],"particularly":[142],"fostering":[144],"diversity":[146],"deliver":[148],"more":[149],"improvements.":[151],"Our":[152],"training":[154],"code":[155],"are":[158],"available":[159],"at":[160],"https://vlf-silkie.github.io.":[161]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2024-10-20T00:00:00"}