{"id":"https://openalex.org/W4408355317","doi":"https://doi.org/10.1109/icassp49660.2025.10889743","title":"Assessing Robustness of Multi-Modal Large Language Models in Image Classification through Hierarchical WordNet-Based Evaluation","display_name":"Assessing Robustness of Multi-Modal Large Language Models in Image Classification through Hierarchical WordNet-Based Evaluation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355317","doi":"https://doi.org/10.1109/icassp49660.2025.10889743"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100353208","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0002-1537-561X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033270758","display_name":"Chen Hai","orcid":"https://orcid.org/0000-0002-3113-252X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Chen","raw_affiliation_strings":["Anhui Unversity,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Unversity,Hefei,China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119962984","display_name":"Boxiang Wang","orcid":"https://orcid.org/0009-0001-2323-2301"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Boxiang Wang","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100775128","display_name":"Shibao Zheng","orcid":"https://orcid.org/0000-0002-5060-0210"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibao Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85597353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5519999861717224,"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":0.5519999861717224,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.529699981212616,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.513700008392334,"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/wordnet","display_name":"WordNet","score":0.8649850487709045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8083893060684204},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7738559246063232},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6538581252098083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6395159959793091},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5426751375198364},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4278194308280945}],"concepts":[{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.8649850487709045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083893060684204},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7738559246063232},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6538581252098083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6395159959793091},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5426751375198364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4278194308280945},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2081580037","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W3034214559","https://openalex.org/W3037492894","https://openalex.org/W3138516171","https://openalex.org/W3153469116","https://openalex.org/W3177096435","https://openalex.org/W4312443924","https://openalex.org/W4386076522","https://openalex.org/W4390873312","https://openalex.org/W4391136507","https://openalex.org/W4401450512","https://openalex.org/W4402670859","https://openalex.org/W4402713111","https://openalex.org/W4402727669","https://openalex.org/W4403943260","https://openalex.org/W4404575065","https://openalex.org/W4410536678","https://openalex.org/W6757555829","https://openalex.org/W6763468762","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6810728803","https://openalex.org/W6845610855","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6852060543","https://openalex.org/W6853116092","https://openalex.org/W6853255756","https://openalex.org/W6854308264","https://openalex.org/W6855350031","https://openalex.org/W6856669996","https://openalex.org/W6857055646","https://openalex.org/W6858247760","https://openalex.org/W6861503643","https://openalex.org/W6868348088","https://openalex.org/W6869027468"],"related_works":["https://openalex.org/W1499795620","https://openalex.org/W112738600","https://openalex.org/W252296781","https://openalex.org/W2135707795","https://openalex.org/W1537146566","https://openalex.org/W2331034580","https://openalex.org/W1517978361","https://openalex.org/W4376623067","https://openalex.org/W3002840018","https://openalex.org/W2040535673"],"abstract_inverted_index":{"The":[0,129],"advancement":[1],"of":[2,33,42,93,175],"multi-modal":[3],"large":[4,59],"language":[5,60],"models":[6,35,61,186],"(MLLMs)":[7],"has":[8],"significantly":[9],"enhanced":[10],"their":[11,27,44,117],"capability":[12],"to":[13,39,72,111,119],"process":[14],"and":[15,23,70,145,184],"understand":[16],"diverse":[17],"data":[18],"types,":[19],"integrating":[20],"text,":[21],"images,":[22],"other":[24,58],"modalities.":[25],"Despite":[26],"impressive":[28],"performance,":[29],"evaluating":[30],"the":[31,40,91,105,120,138,142,146,179],"robustness":[32,74,92],"these":[34,65],"remains":[36],"challenging":[37],"due":[38],"difficulty":[41],"aligning":[43],"text-based":[45],"responses":[46],"with":[47],"image":[48,96],"classification":[49,97,155],"labels.":[50],"Traditional":[51],"approaches":[52],"rely":[53],"on":[54],"CLIP":[55],"scores":[56],"or":[57],"as":[62,125,137],"judges,":[63],"but":[64],"methods":[66],"lack":[67],"scientific":[68],"rigor":[69],"fail":[71],"capture":[73],"across":[75],"different":[76,158],"semantic":[77,159],"levels.":[78,160],"In":[79],"this":[80],"paper,":[81],"we":[82,103,151,164],"propose":[83],"a":[84,126,172],"novel":[85],"evaluation":[86,169],"metric":[87,170],"that":[88,166],"systematically":[89],"assesses":[90],"MLLMs":[94,110],"in":[95,123,187],"using":[98,149],"WordNet\u2019s":[99],"hierarchical":[100],"structure.":[101],"Specifically,":[102],"parse":[104],"text":[106,143],"descriptions":[107],"generated":[108],"by":[109],"extract":[112],"all":[113,133],"nouns,":[114],"then":[115],"calculate":[116],"distances":[118],"groundtruth":[121],"label":[122],"WordNet":[124],"similarity":[127,139],"metric.":[128],"minimum":[130],"distance":[131],"among":[132],"nouns":[134],"is":[135],"used":[136],"score":[140],"between":[141],"description":[144],"label.":[147],"By":[148],"WordNet,":[150],"can":[152],"also":[153],"evaluate":[154],"performance":[156],"at":[157],"Through":[161],"extensive":[162],"experiments,":[163],"demonstrate":[165],"our":[167],"WordNet-based":[168],"offers":[171],"deeper":[173],"understanding":[174],"MLLMs\u2019":[176],"robustness,":[177],"paving":[178],"way":[180],"for":[181],"more":[182],"resilient":[183],"reliable":[185],"real-world":[188],"applications.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}