{"id":"https://openalex.org/W7167928491","doi":"https://doi.org/10.1145/3805712.3809603","title":"RegionSLM: Region-aware Question Answering on Document Screenshots","display_name":"RegionSLM: Region-aware Question Answering on Document Screenshots","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167928491","doi":"https://doi.org/10.1145/3805712.3809603"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809603","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809603","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115605144","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-1297-768X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia and University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1297-768X","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia and University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002207978","display_name":"Hehe Fan","orcid":"https://orcid.org/0000-0001-9572-2345"},"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":"Hehe Fan","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9572-2345","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392975","display_name":"Huichen Yang","orcid":"https://orcid.org/0009-0002-9767-1021"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huichen Yang","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0002-9767-1021","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041251183","display_name":"Sarvnaz Karimi","orcid":"https://orcid.org/0000-0002-4927-3937"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarvnaz Karimi","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia and Monash University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4927-3937","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia and Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"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":"Yi Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-0512-880X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94940951,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1789","last_page":"1799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5943999886512756,"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/T10028","display_name":"Topic Modeling","score":0.5943999886512756,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2298000007867813,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.023099999874830246,"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/relevance","display_name":"Relevance (law)","score":0.8489999771118164},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7825000286102295},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7477999925613403},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5893999934196472},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4918999969959259},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.48829999566078186},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4681999981403351}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8489999771118164},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7825000286102295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627000212669373},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7477999925613403},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6129000186920166},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587999820709229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5378999710083008},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4681999981403351},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.35740000009536743},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809603","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809603","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2986619406","https://openalex.org/W3173585224","https://openalex.org/W3176481196","https://openalex.org/W3200439183","https://openalex.org/W3202839357","https://openalex.org/W4412377016","https://openalex.org/W7137959380"],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"document":[1,170],"question-answering":[2],"that":[3,14,73,100,151],"relies":[4],"on":[5,35,147],"screenshots,":[6],"such":[7],"as":[8],"bills":[9],"and":[10,19,33,46,90,122,134,156,166,172],"forms,":[11],"requires":[12],"evidence":[13],"is":[15,163],"often":[16],"spatially":[17],"localised":[18],"visually":[20],"cluttered.":[21],"However,":[22],"most":[23],"Screenshot":[24],"Language":[25],"Models":[26],"(SLMs)":[27],"encode":[28],"the":[29,58,80],"entire":[30],"page":[31],"holistically":[32],"rely":[34],"implicit":[36],"attention":[37],"to":[38,55,60,82],"''find''":[39],"relevant":[40],"content,":[41],"which":[42,111],"limits":[43],"both":[44],"accuracy":[45],"efficiency.":[47],"We":[48],"present":[49],"RegionSLM,":[50],"a":[51,70,75,84,96,105,128,140],"region-aware":[52],"SLM":[53],"designed":[54],"explicitly":[56,152],"connect":[57],"question":[59],"its":[61],"supporting":[62],"regions.":[63],"RegionSLM":[64],"has":[65],"two":[66],"key":[67],"components:":[68],"(1)":[69],"patch-relevance":[71],"router":[72],"learns":[74],"query\u2013region":[76,154],"relevance":[77,86,155],"distribution,":[78],"enabling":[79],"model":[81],"produce":[83],"box-free":[85],"prior":[87],"at":[88],"inference;":[89],"(2)":[91],"Relevance-Guided":[92],"Region":[93],"Pooling":[94],"(RGRP),":[95],"query-conditional":[97],"attention\u2013pooling":[98],"module":[99],"aggregates":[101],"dense":[102],"features":[103],"into":[104,159],"small":[106],"set":[107],"of":[108],"region":[109,161],"tokens,":[110],"preserves":[112],"grounding":[113],"signals":[114],"while":[115],"reducing":[116],"computational":[117],"overhead.":[118],"To":[119],"support":[120],"training":[121],"evaluation,":[123],"we":[124],"further":[125],"curate":[126],"ReDoc,":[127],"region-supervised":[129],"corpus":[130],"with":[131],"105k":[132],"documents":[133],"350k":[135],"question-answer":[136],"pairs,":[137],"obtained":[138],"via":[139],"question-guided":[141],"two-step":[142],"filtering":[143],"procedure.":[144],"Extensive":[145],"experiments":[146],"12":[148],"datasets":[149],"demonstrate":[150],"learning":[153],"pooling":[157],"it":[158],"compact":[160],"tokens":[162],"an":[164],"effective":[165],"practical":[167],"recipe":[168],"for":[169],"retrieval":[171],"understanding.":[173]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}