{"id":"https://openalex.org/W4403792080","doi":"https://doi.org/10.1145/3664647.3681251","title":"Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs","display_name":"Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792080","doi":"https://doi.org/10.1145/3664647.3681251"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5034937387","display_name":"Peng Ding","orcid":"https://orcid.org/0000-0001-7814-6606"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Ding","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7814-6606","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040080625","display_name":"Jingyu Wu","orcid":"https://orcid.org/0000-0002-2586-330X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Wu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2586-330X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032965844","display_name":"Jun Kuang","orcid":"https://orcid.org/0000-0001-8189-9449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Kuang","raw_affiliation_strings":["Meituan, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8189-9449","affiliations":[{"raw_affiliation_string":"Meituan, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031623126","display_name":"Dan Ma","orcid":"https://orcid.org/0000-0001-9701-2750"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Ma","raw_affiliation_strings":["Meituan, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9701-2750","affiliations":[{"raw_affiliation_string":"Meituan, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108060642","display_name":"Xuezhi Cao","orcid":"https://orcid.org/0000-0002-7044-1341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuezhi Cao","raw_affiliation_strings":["Meituan, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7044-1341","affiliations":[{"raw_affiliation_string":"Meituan, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068562468","display_name":"Xunliang Cai","orcid":"https://orcid.org/0000-0003-0685-9556"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunliang Cai","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0685-9556","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362200","display_name":"Shi Chen","orcid":"https://orcid.org/0000-0002-3577-5725"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Chen","raw_affiliation_strings":["Zhejiang-Singapore Innovation and AI Joint Research Lab, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3577-5725","affiliations":[{"raw_affiliation_string":"Zhejiang-Singapore Innovation and AI Joint Research Lab, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103039793","display_name":"Jiajun Chen","orcid":"https://orcid.org/0000-0002-9859-6898"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chen","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9859-6898","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102865824","display_name":"Shujian Huang","orcid":"https://orcid.org/0000-0003-4869-0832"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujian Huang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4869-0832","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5034937387"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":4.2761,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9421909,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10707","last_page":"10715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.8686000108718872,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.8686000108718872,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13018","display_name":"Seismology and Earthquake Studies","score":0.7889999747276306,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.767799973487854,"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/modal","display_name":"Modal","score":0.6863070130348206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5598381161689758},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4171692430973053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35931694507598877},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.347060889005661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3413509130477905},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.1117422878742218},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05958747863769531}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6863070130348206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5598381161689758},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4171692430973053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35931694507598877},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.347060889005661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3413509130477905},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1117422878742218},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05958747863769531},{"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:10.1145/3664647.3681251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4225323055","https://openalex.org/W4309674289","https://openalex.org/W4404534210"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multi-modal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"demonstrated":[6],"remarkable":[7],"performance":[8],"on":[9,35,143,160],"various":[10],"visual-language":[11],"understanding":[12],"and":[13,120,138,150,196,217,227],"generation":[14],"tasks.":[15,140],"However,":[16],"MLLMs":[17,85,211],"occasionally":[18],"generate":[19],"content":[20],"inconsistent":[21],"with":[22,126,214],"the":[23,44,77,208],"given":[24],"images,":[25],"which":[26,42,111,162],"is":[27,106,163],"known":[28],"as":[29,53,117,148],"\"hallucination\".":[30],"Prior":[31],"works":[32],"primarily":[33],"center":[34],"evaluating":[36],"hallucination":[37,114],"using":[38],"standard,":[39],"unperturbed":[40,167],"benchmarks,":[41],"overlook":[43],"prevalent":[45],"occurrence":[46],"of":[47,64,92,130,183,210],"perturbed":[48,94,98,192,215],"inputs":[49],"in":[50,84,166,176],"real-world":[51],"scenarios-such":[52],"image":[54,105],"cropping":[55],"or":[56],"blurring-that":[57],"are":[58,229],"critical":[59],"for":[60,135,191],"a":[61,127,173],"comprehensive":[62],"assessment":[63],"MLLMs'":[65,177],"hallucination.":[66],"In":[67],"this":[68,72,223],"paper,":[69],"to":[70,81,179,207,221],"bridge":[71],"gap,":[73],"we":[74],"propose":[75],"Hallu-PI,":[76,161],"first":[78],"benchmark":[79],"designed":[80],"evaluate":[82],"Hallucination":[83],"within":[86],"Perturbed":[87],"Inputs.":[88],"Specifically,":[89],"Hallu-PI":[90,133],"consists":[91],"seven":[93],"scenarios,":[95,193],"containing":[96],"1,260":[97],"images":[99],"from":[100],"11":[101],"object":[102],"types.":[103],"Each":[104],"accompanied":[107],"by":[108],"detailed":[109],"annotations,":[110],"include":[112],"fine-grained":[113],"types,":[115],"such":[116,147],"existence,":[118],"attribute,":[119],"relation.":[121],"We":[122,185,198],"equip":[123],"these":[124,155],"annotations":[125],"rich":[128],"set":[129],"questions,":[131],"making":[132],"suitable":[134],"both":[136],"discriminative":[137],"generative":[139],"Extensive":[141],"experiments":[142],"12":[144],"mainstream":[145],"MLLMs,":[146],"GPT-4V":[149],"Gemini-Pro":[151],"Vision,":[152],"demonstrate":[153],"that":[154,200],"models":[156],"exhibit":[157],"significant":[158],"hallucinations":[159],"not":[164],"observed":[165],"scenarios.":[168],"Furthermore,":[169],"our":[170,201],"research":[171],"reveals":[172],"severe":[174],"bias":[175],"ability":[178],"handle":[180],"different":[181],"types":[182],"hallucinations.":[184],"also":[186],"design":[187],"two":[188],"baselines":[189],"specifically":[190],"namely":[194],"Perturbed-Reminder":[195],"Perturbed-ICL.":[197],"hope":[199],"study":[202],"will":[203],"bring":[204],"researchers'":[205],"attention":[206],"limitations":[209],"when":[212],"dealing":[213],"inputs,":[216],"spur":[218],"further":[219],"investigations":[220],"address":[222],"issue.":[224],"Our":[225],"code":[226],"datasets":[228],"publicly":[230],"available":[231],"at":[232],"https://github.com/NJUNLP/Hallu-PI.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}