{"id":"https://openalex.org/W7157637492","doi":"https://doi.org/10.48550/arxiv.2604.25420","title":"Recommending Usability Improvements with Multimodal Large Language Models","display_name":"Recommending Usability Improvements with Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-04-28","ids":{"openalex":"https://openalex.org/W7157637492","doi":"https://doi.org/10.48550/arxiv.2604.25420"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.25420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.25420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040617592","display_name":"Sebastian Lubos","orcid":"https://orcid.org/0000-0002-5024-3786"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lubos, Sebastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033783997","display_name":"Alexander Felfernig","orcid":"https://orcid.org/0000-0003-0108-3146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felfernig, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092697129","display_name":"Damian Garber","orcid":"https://orcid.org/0009-0005-0993-0911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garber, Damian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010230805","display_name":"Viet-Man Le","orcid":"https://orcid.org/0000-0001-5778-975X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Viet-Man","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055288736","display_name":"Manuel Henrich","orcid":"https://orcid.org/0000-0002-9957-9993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Henrich, Manuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10470","display_name":"Usability and User Interface Design","score":0.7310000061988831,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10470","display_name":"Usability and User Interface Design","score":0.7310000061988831,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.07580000162124634,"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/T14074","display_name":"Persona Design and Applications","score":0.025699999183416367,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/usability","display_name":"Usability","score":0.9164999723434448},{"id":"https://openalex.org/keywords/usability-engineering","display_name":"Usability engineering","score":0.7555999755859375},{"id":"https://openalex.org/keywords/usability-goals","display_name":"Usability goals","score":0.7210000157356262},{"id":"https://openalex.org/keywords/cognitive-walkthrough","display_name":"Cognitive walkthrough","score":0.70660001039505},{"id":"https://openalex.org/keywords/usability-inspection","display_name":"Usability inspection","score":0.6244999766349792},{"id":"https://openalex.org/keywords/usability-lab","display_name":"Usability lab","score":0.5788999795913696},{"id":"https://openalex.org/keywords/web-usability","display_name":"Web usability","score":0.5465999841690063},{"id":"https://openalex.org/keywords/system-usability-scale","display_name":"System usability scale","score":0.49869999289512634}],"concepts":[{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.9164999723434448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660999894142151},{"id":"https://openalex.org/C100302975","wikidata":"https://www.wikidata.org/wiki/Q1642623","display_name":"Usability engineering","level":3,"score":0.7555999755859375},{"id":"https://openalex.org/C62993174","wikidata":"https://www.wikidata.org/wiki/Q2928808","display_name":"Usability goals","level":4,"score":0.7210000157356262},{"id":"https://openalex.org/C87105883","wikidata":"https://www.wikidata.org/wiki/Q1107002","display_name":"Cognitive walkthrough","level":4,"score":0.70660001039505},{"id":"https://openalex.org/C23456302","wikidata":"https://www.wikidata.org/wiki/Q7901668","display_name":"Usability inspection","level":4,"score":0.6244999766349792},{"id":"https://openalex.org/C11324603","wikidata":"https://www.wikidata.org/wiki/Q2502322","display_name":"Usability lab","level":4,"score":0.5788999795913696},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5551000237464905},{"id":"https://openalex.org/C4237393","wikidata":"https://www.wikidata.org/wiki/Q1636686","display_name":"Web usability","level":3,"score":0.5465999841690063},{"id":"https://openalex.org/C139225968","wikidata":"https://www.wikidata.org/wiki/Q17146354","display_name":"System usability scale","level":4,"score":0.49869999289512634},{"id":"https://openalex.org/C188688815","wikidata":"https://www.wikidata.org/wiki/Q7205541","display_name":"Pluralistic walkthrough","level":3,"score":0.47099998593330383},{"id":"https://openalex.org/C3255780","wikidata":"https://www.wikidata.org/wiki/Q1616517","display_name":"Heuristic evaluation","level":3,"score":0.45730000734329224},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C71151206","wikidata":"https://www.wikidata.org/wiki/Q5156686","display_name":"Component-based usability testing","level":5,"score":0.3716999888420105},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35989999771118164},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.25420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.25420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4305154085159302,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Usability":[0],"describes":[1,134],"quality":[2,164],"attributes":[3],"of":[4,54,71,91,97,121,154,168,201],"application":[5,116],"user":[6,49,122,177],"interfaces":[7],"that":[8,113,179],"determine":[9],"how":[10],"effectively":[11],"users":[12],"can":[13,27,75],"interact":[14],"with":[15,223],"them.":[16],"Traditional":[17],"usability":[18,37,67,92,135,140,207,227,247],"evaluation":[19,38,68,186,218,248],"methods":[20],"require":[21],"considerable":[22],"expertise":[23],"and":[24,34,44,69,82,94,118,133,142,146,165],"resources,":[25],"which":[26,87],"be":[28],"challenging,":[29],"especially":[30,220],"for":[31,65,238],"small":[32],"teams":[33],"organizations.":[35],"Automating":[36],"could":[39],"make":[40],"it":[41,212],"more":[42],"accessible":[43],"help":[45],"to":[46,100,126,204,216,226,244],"improve":[47],"the":[48,89,95,151,157,169,189,194,199,232],"experience.":[50],"The":[51,129,163,185,196],"recent":[52],"emergence":[53],"powerful":[55],"multimodal":[56],"large":[57],"language":[58],"models":[59,74],"(MLLMs)":[60],"has":[61],"opened":[62],"new":[63],"opportunities":[64],"automating":[66],"recommendation":[70],"improvements.":[72],"These":[73],"process":[76],"visual":[77],"inputs":[78],"such":[79],"as":[80,124,183,235],"images":[81],"videos":[83],"alongside":[84],"textual":[85],"context,":[86],"enables":[88],"identification":[90],"issues":[93,136],"generation":[96],"actionable":[98],"suggestions":[99,191],"resolve":[101],"these":[102],"issues.":[103],"In":[104,229],"this":[105,230],"paper,":[106],"we":[107],"present":[108],"a":[109,176,213,236],"novel":[110],"automated":[111,246],"approach":[112,203,233],"uses":[114],"limited":[115,224],"context":[117],"screen":[119],"recordings":[120],"interactions":[123],"input":[125],"an":[127],"MLLM.":[128],"model":[130],"automatically":[131],"identifies":[132],"based":[137,174],"on":[138,175,188],"Nielsens":[139],"heuristics,":[141],"provides":[143],"corresponding":[144],"explanations":[145],"improvement":[147,208],"recommendations.":[148,209],"To":[149],"reduce":[150],"developer":[152],"effort":[153],"manual":[155],"prioritization,":[156],"recommendations":[158,171],"are":[159],"ranked":[160],"by":[161,193],"severity.":[162],"practical":[166],"usefulness":[167],"generated":[170],"were":[172],"evaluated":[173],"study":[178],"involved":[180],"software":[181,250],"engineers":[182],"participants.":[184],"focused":[187],"highest-ranked":[190],"provided":[192],"model.":[195],"results":[197],"demonstrate":[198],"potential":[200],"our":[202],"provide":[205],"low-effort":[206],"This":[210],"makes":[211],"promising":[214],"complement":[215],"traditional":[217],"methods,":[219],"in":[221],"settings":[222],"access":[225],"experts.":[228],"sense,":[231],"serves":[234],"basis":[237],"future":[239],"integration":[240],"into":[241],"development":[242],"tools":[243],"enable":[245],"within":[249],"engineering":[251],"workflows.":[252]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-30T00:00:00"}
