{"id":"https://openalex.org/W7140114495","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.144","title":"Do GUI Grounders Truly Understand UI Elements?","display_name":"Do GUI Grounders Truly Understand UI Elements?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140114495","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.144"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.144","pdf_url":"https://aclanthology.org/2026.findings-eacl.144.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.144.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046611496","display_name":"Surgan Jandial","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Surgan Jandial","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130403914","display_name":"Yinheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130407981","display_name":"Justin Wagle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Justin Wagle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2772","last_page":"2785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14056","display_name":"Safety Warnings and Signage","score":0.08060000091791153,"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/T14056","display_name":"Safety Warnings and Signage","score":0.08060000091791153,"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/T10470","display_name":"Usability and User Interface Design","score":0.05770000070333481,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.04740000143647194,"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/key","display_name":"Key (lock)","score":0.527899980545044},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.49549999833106995},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4950999915599823},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.48590001463890076},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.44600000977516174},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.40619999170303345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663999795913696},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6021999716758728},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.46140000224113464},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2526000142097473},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.144","pdf_url":"https://aclanthology.org/2026.findings-eacl.144.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.144","pdf_url":"https://aclanthology.org/2026.findings-eacl.144.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140114495.pdf","grobid_xml":"https://content.openalex.org/works/W7140114495.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graphical":[0],"User":[1],"Interface":[2],"(GUI)":[3],"grounding":[4,18,36,70,155,196],"is":[5,38,257,294],"critical":[6],"for":[7],"effective":[8],"GUI":[9,84,167,195,239,246],"agents.Despite":[10],"recent":[11],"progress,":[12],"key":[13],"challenges":[14],"remain:":[15],"1)":[16],"existing":[17,141],"models":[19,121,131],"and":[20,26,34,67,113,137,178],"benchmarks":[21,142],"are":[22,134],"skewed":[23],"toward":[24],"web":[25],"mobile":[27],"environments,":[28,81],"neglecting":[29],"desktop":[30,80],"interfaces":[31],"(especially":[32],"windows);":[33],"2)":[35],"capability":[37],"assessed":[39],"using":[40,175],"accuracy":[41],"on":[42,79,140,149],"a":[43,54,68,126,153,275,291],"single":[44,127],"\"best\"":[45],"instruction":[46],"per":[47,110],"UI":[48,55,99,111,244,255,276,292],"element.However,":[49],"users":[50],"can":[51,278],"refer":[52],"to":[53,93,105,124,209,219,229,272],"element":[56,256,277,293],"in":[57,188,201,303],"diverse":[58],"valid":[59,108],"ways":[60],"-via":[61],"visual":[62],"attributes,":[63],"spatial":[64],"relations,":[65,163],"etc,":[66],"capable":[69],"model":[71,91,156,176,289],"should":[72],"produce":[73,125],"consistent":[74],"outputs":[75],"across":[76],"such":[77],"variations.Focusing":[78],"we":[82,164],"introduce":[83,165],"Grounding":[85,168,240,247,288],"Sensitivity":[86],"Benchmark,":[87],"which":[88,171],"investigates":[89],"the":[90,97,150,166,193,198,202,206,210,216,220,226,230,253,263,287],"sensitivity":[92],"multiple":[94,107,282,297],"descriptions":[95],"of":[96,129,213,223,233,306],"same":[98,254],"element.We":[100],"design":[101],"an":[102],"automatic":[103],"pipeline":[104],"generate":[106],"instructions":[109,161,174,190],"element,":[112],"develop":[114],"nuanced":[115],"data":[116],"validation":[117],"methods,":[118],"as":[119],"frontier":[120],"even":[122],"hallucinate":[123],"instruction.Evaluation":[128],"12":[130],"reveals":[132],"they":[133],"reasonably":[135],"sensitive":[136],"their":[138,146],"performance":[139],"does":[143],"not":[144],"reflect":[145],"true":[147],"ability.Building":[148],"insight":[151],"that":[152,191,274],"given":[154],"struggles":[157],"more":[158],"with":[159],"certain":[160],"or":[162],"Diagnosis":[169],"Agent,":[170],"generates":[172],"challenging":[173],"feedback":[177],"iterative":[179],"refinement.Our":[180],"agent":[181],"reports":[182],"high":[183],"success":[184],"rate":[185],"(upto":[186],"84%)":[187],"generating":[189],"fail":[192,271],"state-of-the-art":[194],"models.Click":[197],"Omega":[199],"symbol":[200],"Insert":[203],"ribbon":[204],"Click":[205,215,225,299],"omega":[207,217],"button":[208,218],"immediate":[211,221,231],"right":[212,222],"Equation":[214,224],"drop-down":[227],"arrow":[228],"left":[232],"Number":[234],"UI-TARS":[235],"-1.5":[236],"7B":[237,261],"Do":[238],"Models":[241,248],"Truly":[242],"Understand":[243],"Elements?Do":[245],"make":[249],"Consistent":[250],"Predictions":[251],"when":[252,290],"described":[258,295],"differently?UGround":[259],"-V1":[260],"Open":[262],"stata":[264],"app":[265],"from":[266,281,296],"taskbar":[267],"(a)":[268],"Existing":[269],"Works":[270],"consider":[273],"be":[279],"referred":[280],"perspectives":[283,298],"(b)":[284],"We":[285],"investigate":[286],"third":[300],"color":[301,307],"option":[302],"first":[304],"row":[305],"selection":[308],"panel":[309],"under":[310],"'Customize":[311],"Chrome'":[312],"section.":[313]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}
