{"id":"https://openalex.org/W4388926389","doi":"https://doi.org/10.48550/arxiv.2311.11904","title":"LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions","display_name":"LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4388926389","doi":"https://doi.org/10.48550/arxiv.2311.11904"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.11904","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.11904","pdf_url":"https://arxiv.org/pdf/2311.11904","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/2311.11904","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049392540","display_name":"Songhao Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Han, Songhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100310256","display_name":"Le Zhuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo, Le","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002061412","display_name":"Yue Liao","orcid":"https://orcid.org/0000-0002-2671-0655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Si","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049392540"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.9972000122070312,"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":0.9972000122070312,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.963100016117096,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9563000202178955,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.8247406482696533},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6521838903427124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6515499353408813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6498907208442688},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6185486912727356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.548137366771698},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45837047696113586},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3366376757621765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32985028624534607}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.8247406482696533},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6521838903427124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6515499353408813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6498907208442688},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6185486912727356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.548137366771698},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45837047696113586},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3366376757621765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32985028624534607},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.11904","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.11904","pdf_url":"https://arxiv.org/pdf/2311.11904","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.2311.11904","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.11904","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:2311.11904","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.11904","pdf_url":"https://arxiv.org/pdf/2311.11904","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":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388926389.pdf","grobid_xml":"https://content.openalex.org/works/W4388926389.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W1489772951"],"abstract_inverted_index":{"Vision-language":[0],"models":[1,41,169],"(VLMs)":[2],"offer":[3,159],"a":[4,73,105,151],"promising":[5],"paradigm":[6],"for":[7,28,81],"image":[8],"classification":[9,148],"by":[10],"comparing":[11],"the":[12,63,84,87,115],"similarity":[13],"between":[14,75],"images":[15],"and":[16,53,78,111,161,170],"class":[17,29,117,134],"embeddings.":[18],"A":[19],"critical":[20],"challenge":[21],"lies":[22],"in":[23,38,91],"crafting":[24],"precise":[25],"textual":[26,67],"representations":[27],"names.":[30],"While":[31],"previous":[32],"studies":[33],"have":[34],"leveraged":[35],"recent":[36],"advancements":[37],"large":[39],"language":[40],"(LLMs)":[42],"to":[43,58,72,95,113,131],"enhance":[44],"these":[45,157],"descriptors,":[46],"their":[47],"outputs":[48],"often":[49],"suffer":[50],"from":[51],"ambiguity":[52],"inaccuracy.":[54],"We":[55,136],"attribute":[56],"this":[57,101],"two":[59],"primary":[60],"factors:":[61],"1)":[62],"reliance":[64],"on":[65,150],"single-turn":[66],"interactions":[68],"with":[69,126],"LLMs,":[70],"leading":[71],"mismatch":[74],"generated":[76],"text":[77],"visual":[79],"concepts":[80],"VLMs;":[82],"2)":[83],"oversight":[85],"of":[86,142,154],"inter-class":[88],"relationships,":[89],"resulting":[90],"descriptors":[92,140,158],"that":[93,108],"fail":[94],"differentiate":[96],"similar":[97],"classes":[98],"effectively.":[99],"In":[100],"paper,":[102],"we":[103],"propose":[104],"novel":[106],"framework":[107],"integrates":[109],"LLMs":[110],"VLMs":[112],"find":[114],"optimal":[116],"descriptors.":[118,135],"Our":[119],"training-free":[120],"approach":[121],"develops":[122],"an":[123,127],"LLM-based":[124],"agent":[125],"evolutionary":[128],"optimization":[129],"strategy":[130],"iteratively":[132],"refine":[133],"demonstrate":[137],"our":[138],"optimized":[139],"are":[141],"high":[143],"quality":[144],"which":[145],"effectively":[146],"improves":[147],"accuracy":[149],"wide":[152],"range":[153],"benchmarks.":[155],"Additionally,":[156],"explainable":[160],"robust":[162],"features,":[163],"boosting":[164],"performance":[165],"across":[166],"various":[167],"backbone":[168],"complementing":[171],"fine-tuning-based":[172],"methods.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2023-11-23T00:00:00"}