{"id":"https://openalex.org/W7125907148","doi":"https://doi.org/10.1109/ase63991.2025.00380","title":"TrustVis: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models","display_name":"TrustVis: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7125907148","doi":"https://doi.org/10.1109/ase63991.2025.00380"},"language":null,"primary_location":{"id":"doi:10.1109/ase63991.2025.00380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","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/A5124141097","display_name":"Ruoyu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ruoyu Sun","raw_affiliation_strings":["University of Alberta,Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta,Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076472355","display_name":"Da Song","orcid":"https://orcid.org/0000-0001-8064-3409"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Da Song","raw_affiliation_strings":["Mila - Quebec Artificial Intelligence Institute"],"affiliations":[{"raw_affiliation_string":"Mila - Quebec Artificial Intelligence Institute","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124141431","display_name":"Jiayang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jiayang Song","raw_affiliation_strings":["Macau University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Macau University of Science and Technology,China","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761814","display_name":"Yuheng Huang","orcid":"https://orcid.org/0009-0009-7336-9670"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuheng Huang","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124095323","display_name":"Lei Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lei Ma","raw_affiliation_strings":["University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5124141097"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87682743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4082","last_page":"4085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3122999966144562,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3122999966144562,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.16779999434947968,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15230000019073486,"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/trustworthiness","display_name":"Trustworthiness","score":0.6991999745368958},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5220000147819519},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.448199987411499},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.38830000162124634},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37599998712539673},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.335999995470047},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.3222000002861023},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3181999921798706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964000105857849},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6991999745368958},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5220000147819519},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.448199987411499},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43939998745918274},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2957000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ase63991.2025.00380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ase63991.2025.00380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6503861546516418,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1608512056","https://openalex.org/W1982147649","https://openalex.org/W4285113702","https://openalex.org/W4320342906","https://openalex.org/W4392669753","https://openalex.org/W4399768519","https://openalex.org/W4404783422"],"related_works":[],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2,9],"Models":[3],"(LLMs)":[4],"continue":[5],"to":[6,55,90,120],"revolutionize":[7],"Natural":[8],"Processing":[10],"(NLP)":[11],"applications,":[12],"critical":[13],"concerns":[14],"about":[15],"their":[16],"trustworthiness":[17,60],"persist,":[18],"particularly":[19],"in":[20,108,123],"safety":[21,110],"and":[22,69,100,111],"robustness.":[23],"To":[24],"address":[25],"these":[26],"challenges,":[27],"we":[28],"introduce":[29],"TrustVis,":[30],"an":[31],"automated":[32],"evaluation":[33,75,87],"framework":[34,48,107],"that":[35],"provides":[36,80],"a":[37],"comprehensive":[38],"assessment":[39],"of":[40,46,59,105],"LLM":[41],"trustworthiness.":[42],"A":[43],"key":[44],"feature":[45],"our":[47,106],"is":[49],"its":[50],"interactive":[51,116],"user":[52],"interface,":[53],"designed":[54],"offer":[56],"intuitive":[57],"visualizations":[58],"metrics.":[61],"By":[62],"integrating":[63],"well-known":[64],"perturbation":[65],"methods":[66],"like":[67,97],"AutoDAN":[68],"employing":[70],"majority":[71],"voting":[72],"across":[73],"various":[74],"methods,":[76],"TrustVis":[77],"not":[78],"only":[79],"reliable":[81],"results":[82,122],"but":[83],"also":[84],"makes":[85],"complex":[86],"processes":[88],"accessible":[89],"users.":[91],"Preliminary":[92],"case":[93],"studies":[94],"on":[95],"models":[96],"Vicuna-7b,":[98],"Llama2-7b,":[99],"GPT-3.5":[101],"demonstrate":[102],"the":[103,115],"effectiveness":[104],"identifying":[109],"robustness":[112],"vulnerabilities,":[113],"while":[114],"interface":[117],"allows":[118],"users":[119],"explore":[121],"detail,":[124],"empowering":[125],"targeted":[126],"model":[127],"improvements.":[128],"Video":[129],"Link:":[130],"https://youtu.be/k1TrBqNVg8g":[131]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}
