{"id":"https://openalex.org/W7162630891","doi":"https://doi.org/10.1145/3774905.3793117","title":"Docs2Synth: A Synthetic Data Tuned Retriever Framework for Documents Understanding","display_name":"Docs2Synth: A Synthetic Data Tuned Retriever Framework for Documents Understanding","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162630891","doi":"https://doi.org/10.1145/3774905.3793117"},"language":"en","primary_location":{"id":"doi:10.1145/3774905.3793117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774905.3793117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","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/A5137249892","display_name":"Yihao Ding","orcid":"https://orcid.org/0000-0001-5065-6911"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yihao Ding","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5065-6911","affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073178764","display_name":"Qiang Sun","orcid":"https://orcid.org/0000-0002-4445-0025"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiang Sun","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4445-0025","affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137263559","display_name":"Puzhen Wu","orcid":"https://orcid.org/0000-0003-1510-215X"},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Puzhen Wu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-1510-215X","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137252836","display_name":"Sirui Li","orcid":"https://orcid.org/0000-0002-2504-3790"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sirui Li","raw_affiliation_strings":["Murdoch University, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2504-3790","affiliations":[{"raw_affiliation_string":"Murdoch University, Perth, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078732700","display_name":"Siwen Luo","orcid":"https://orcid.org/0000-0003-0480-1991"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Siwen Luo","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0480-1991","affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137286967","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-7409-0948"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7409-0948","affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"124","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1395999938249588,"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":0.1395999938249588,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.10970000177621841,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.09440000355243683,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/synthetic-data","display_name":"Synthetic data","score":0.34540000557899475},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3000999987125397},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2815000116825104},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.27320000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5568000078201294},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2362000048160553}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3774905.3793117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774905.3793117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/fa4d64b6-32ca-4f52-aa2b-58c1eb526349","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/fa4d64b6-32ca-4f52-aa2b-58c1eb526349","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ding, Y, Sun, Q, Wu, P, Li, S, Luo, S & Liu, W 2026, Docs2Synth : A Synthetic Data Tuned Retriever Framework for Documents Understanding. in WWW Companion 2026 - Companion Proceedings of the ACM Web Conference 2026. WWW Companion 2026 - Companion Proceedings of the ACM Web Conference 2026, Association for Computing Machinery (ACM), pp. 124-127. https://doi.org/10.1145/3774905.3793117","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3132296545","https://openalex.org/W4304013646","https://openalex.org/W4381708538","https://openalex.org/W4384636790","https://openalex.org/W4385571998","https://openalex.org/W4388926270","https://openalex.org/W4390214291","https://openalex.org/W4402683733","https://openalex.org/W4402702988","https://openalex.org/W4402727764","https://openalex.org/W4403853618","https://openalex.org/W4404782234"],"related_works":[],"abstract_inverted_index":{"Document":[0],"understanding":[1],"(VRDU)":[2],"in":[3],"regulated":[4],"domains":[5],"is":[6,182,190],"particularly":[7],"challenging,":[8],"since":[9],"scanned":[10],"documents":[11],"often":[12],"contain":[13],"sensitive,":[14],"evolving,":[15],"and":[16,34,61,95,105,114,141,172,186],"domain":[17,63,173],"specific":[18],"knowledge.":[19],"This":[20],"leads":[21],"to":[22,40,79,120],"two":[23],"major":[24],"challenges:":[25],"the":[26,35,126,187],"lack":[27],"of":[28],"manual":[29],"annotations":[30,78],"for":[31,37,93],"model":[32],"adaptation":[33],"difficulty":[36],"pretrained":[38],"models":[39],"stay":[41],"up-to-date":[42],"with":[43,129],"domain-specific":[44],"facts.":[45],"While":[46],"Multimodal":[47],"Large":[48],"Language":[49],"Models":[50,70],"(MLLMs)":[51],"show":[52,166],"strong":[53],"zero-shot":[54],"abilities,":[55],"they":[56],"still":[57],"suffer":[58],"from":[59],"hallucination":[60,140],"limited":[62],"grounding.":[64],"In":[65],"contrast,":[66],"discriminative":[67],"Vision-Language":[68],"Pre-trained":[69],"(VLPMs)":[71],"provide":[72],"reliable":[73],"grounding":[74,171],"but":[75],"require":[76],"costly":[77],"cover":[80],"new":[81],"domains.":[82,97],"We":[83,145],"introduce":[84],"Docs2Synth,":[85],"a":[86,116],"synthetic-supervision":[87],"framework":[88],"that":[89,167],"enables":[90],"retrieval-guided":[91],"inference":[92],"private":[94],"low-resource":[96],"Docs2Synth":[98,148,168],"automatically":[99],"processes":[100],"raw":[101],"document":[102],"collections,":[103],"generates":[104],"verifies":[106],"diverse":[107,158],"QA":[108],"pairs":[109],"via":[110],"an":[111,130,133,150],"agent-based":[112],"system,":[113],"trains":[115],"lightweight":[117],"visual":[118],"retriever":[119,127],"extract":[121],"domain-relevant":[122],"evidence.":[123],"During":[124],"inference,":[125],"collaborates":[128],"MLLM":[131],"through":[132],"iterative":[134],"retrieval":[135],"-":[136],"generation":[137],"loop,":[138],"reducing":[139],"improving":[142],"response":[143],"consistency.":[144],"further":[146],"deliver":[147],"as":[149],"easy-to-use":[151],"Python":[152],"package,":[153],"enabling":[154],"plug-and-play":[155],"deployment":[156],"across":[157],"real-world":[159],"scenarios.":[160],"Experiments":[161],"on":[162],"multiple":[163],"VRDU":[164],"benchmarks":[165],"substantially":[169],"enhances":[170],"generalization":[174],"without":[175],"requiring":[176],"human":[177],"annotations.":[178],"Our":[179],"open-source":[180],"implementation":[181],"available":[183,191],"at:":[184],"https://docs2synth.ai4wa.com,":[185],"demonstration":[188],"video":[189],"at":[192],"https://docs2synth.ai4wa.com/video.":[193]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-29T00:00:00"}