{"id":"https://openalex.org/W7164867029","doi":"https://doi.org/10.1145/3805622.3810787","title":"Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety","display_name":"Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164867029","doi":"https://doi.org/10.1145/3805622.3810787"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810787","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810787","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810787","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103333525","display_name":"Junliang Liu","orcid":"https://orcid.org/0000-0002-1313-5073"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Liu","raw_affiliation_strings":["Dalian Maritime University\u200c, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0004-1072-5539","affiliations":[{"raw_affiliation_string":"Dalian Maritime University\u200c, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033074326","display_name":"Jingyu Xiao","orcid":"https://orcid.org/0000-0002-2394-2995"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingyu Xiao","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2394-2995","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101133015","display_name":"Wenxin Tang","orcid":"https://orcid.org/0000-0002-9156-0251"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Tang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9156-0251","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138663062","display_name":"Zhixian Wang","orcid":"https://orcid.org/0009-0000-9503-2109"},"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":"Zhixian Wang","raw_affiliation_strings":["Nanyang Technological University\u200c, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0000-9503-2109","affiliations":[{"raw_affiliation_string":"Nanyang Technological University\u200c, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138665556","display_name":"Zipeng Xie","orcid":"https://orcid.org/0009-0004-6095-7979"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zipeng Xie","raw_affiliation_strings":["\u200cXi'an Jiaotong University\u200c, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0004-6095-7979","affiliations":[{"raw_affiliation_string":"\u200cXi'an Jiaotong University\u200c, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106746626","display_name":"Wenxuan Wang","orcid":"https://orcid.org/0000-0002-9803-8204"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Wang","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9803-8204","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035655380","display_name":"Minrun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minrun Zhang","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0007-9572-9820","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061215099","display_name":"Shuanghe Yu","orcid":"https://orcid.org/0000-0001-6882-2711"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangheng Yu","raw_affiliation_strings":["Dalian Maritime University\u200c, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6882-2711","affiliations":[{"raw_affiliation_string":"Dalian Maritime University\u200c, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"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":"2182","last_page":"2190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10470","display_name":"Usability and User Interface Design","score":0.1891999989748001,"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":0.1891999989748001,"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":0.1168999969959259,"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/T10799","display_name":"Data Visualization and Analytics","score":0.11259999871253967,"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/robustness","display_name":"Robustness (evolution)","score":0.6668999791145325},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6191999912261963},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.5236999988555908},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5110999941825867},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.3871999979019165},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.37709999084472656},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3287000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034000158309937},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6668999791145325},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C137726913","wikidata":"https://www.wikidata.org/wiki/Q7353550","display_name":"Robustness testing","level":3,"score":0.27090001106262207}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810787","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810787","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810787","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810787","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4459030330181122,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3121976951","https://openalex.org/W4402716477","https://openalex.org/W4402753874","https://openalex.org/W4404356447","https://openalex.org/W4409671919","https://openalex.org/W4411119485","https://openalex.org/W4411120254","https://openalex.org/W4412887860","https://openalex.org/W4412888064","https://openalex.org/W4412945435","https://openalex.org/W4416036752"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3,156],"(MLLMs)":[4],"are":[5,187,203],"increasingly":[6],"deployed":[7],"as":[8,85,179],"the":[9,50,63],"core":[10],"reasoning":[11,163],"engine":[12],"for":[13,57],"web-facing":[14],"systems,":[15],"powering":[16],"GUI":[17],"agents":[18],"and":[19,30,53,79,91,103,117,130,134,161,176,186,192,201],"front-end":[20],"automation":[21],"that":[22,74,108],"must":[23],"interpret":[24],"page":[25,113],"structure,":[26,114],"select":[27],"actionable":[28],"widgets,":[29,116],"execute":[31],"multi-step":[32,110],"interactions":[33],"reliably.":[34],"However,":[35],"existing":[36],"benchmarks":[37],"largely":[38],"emphasize":[39],"visual":[40,183],"perception":[41],"or":[42,182,196],"UI":[43],"code":[44,200],"generation,":[45],"showing":[46],"insufficient":[47],"evaluation":[48,132],"on":[49,149],"reasoning,":[51,88],"robustness":[52,169],"safety":[54,92,194],"capability":[55],"required":[56],"end-to-end":[58],"web":[59,69],"applications.":[60],"To":[61,120],"bridge":[62],"gap,":[64],"we":[65,124],"introduce":[66],"a":[67,128],"comprehensive":[68],"understanding":[70],"benchmark,":[71],"named":[72],"WebRRSBench,":[73],"jointly":[75],"evaluates":[76],"Reasoning,":[77],"Robustness,":[78],"Safety":[80],"across":[81],"eight":[82],"tasks,":[83],"such":[84,178],"position":[86],"relationship":[87],"color":[89],"robustness,":[90],"critical":[93,195],"detection,":[94],"etc.":[95],"The":[96,151],"benchmark":[97],"is":[98],"constructed":[99],"from":[100],"729":[101],"websites":[102],"contains":[104],"3799":[105],"QA":[106],"pairs":[107],"probe":[109],"inference":[111],"over":[112,164],"text,":[115],"safety-critical":[118],"interactions.":[119],"ensure":[121],"reliable":[122],"measurement,":[123],"adopt":[125],"standardized":[126],"prompts,":[127],"protocolized":[129],"deterministic":[131],"pipeline,":[133],"multi-stage":[135],"quality":[136],"control":[137],"combining":[138],"automatic":[139],"checks":[140],"with":[141,159],"targeted":[142],"human":[143],"verification.":[144],"We":[145],"evaluate":[146],"11":[147],"MLLMs":[148],"WebRRSBench.":[150],"results":[152],"reveal":[153],"significant":[154],"gaps:":[155],"still":[157],"struggle":[158],"compositional":[160],"cross-element":[162],"realistic":[165],"layouts,":[166],"show":[167],"limited":[168],"when":[170],"facing":[171],"perturbations":[172],"in":[173,190],"user":[174],"interfaces":[175],"content":[177],"layout":[180],"rearrangements":[181],"style":[184],"shifts,":[185],"rather":[188],"conservative":[189],"recognizing":[191],"avoiding":[193],"irreversible":[197],"actions.":[198],"Our":[199],"appendix":[202],"available":[204],"at":[205],"https://github.com/JunliangLiu-repo/WebRRSBench.":[206]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-16T00:00:00"}
