{"id":"https://openalex.org/W7166796205","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1135","title":"ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction","display_name":"ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166796205","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1135"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1135","pdf_url":"https://aclanthology.org/2026.findings-acl.1135.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: ACL 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-acl.1135.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139745089","display_name":"Zichun Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zichun Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139803346","display_name":"Yuling Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuling Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004051832","display_name":"Wenhao Zeng","orcid":"https://orcid.org/0009-0008-1211-1302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139830853","display_name":"Chao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126679734","display_name":"Haotian Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haotian Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139765374","display_name":"Terry Yue Zhuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Terry Yue Zhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139756132","display_name":"Jiawei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771290","display_name":"Xiaodong Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139837865","display_name":"Wenping Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenping Ma","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78588148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22603","last_page":"22615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5054000020027161,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.5054000020027161,"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/T10028","display_name":"Topic Modeling","score":0.2574000060558319,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.07959999889135361,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.424699991941452},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.34540000557899475},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3206999897956848},{"id":"https://openalex.org/keywords/legibility","display_name":"Legibility","score":0.29330000281333923},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.29089999198913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48570001125335693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1135","pdf_url":"https://aclanthology.org/2026.findings-acl.1135.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1135","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1135","pdf_url":"https://aclanthology.org/2026.findings-acl.1135.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4906496431","display_name":null,"funder_award_id":"2023YFB4503802","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166796205.pdf","grobid_xml":"https://content.openalex.org/works/W7166796205.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"achieved":[6],"remarkable":[7],"performance":[8,119],"in":[9,165],"Visually":[10],"Rich":[11],"Document":[12],"Understanding":[13],"(VRDU)":[14],"tasks,":[15,56],"but":[16],"their":[17],"capabilities":[18],"are":[19],"mainly":[20],"evaluated":[21],"on":[22,113,125],"pristine,":[23],"well-structured":[24],"document":[25,131],"images.We":[26],"consider":[27],"content":[28,48],"restoration":[29,134],"from":[30,73],"shredded":[31],"fragments,":[32],"a":[33,60,117,136,162],"challenging":[34],"VRDU":[35,55,167],"setting":[36],"that":[37,68,148],"requires":[38],"integrating":[39],"visual":[40,159],"pattern":[41],"recognition":[42],"with":[43,104,139],"semantic":[44],"reasoning":[45,155],"under":[46],"significant":[47,118,137],"discontinuities.To":[49],"facilitate":[50],"systematic":[51],"evaluation":[52,78],"of":[53,85],"complex":[54],"we":[57],"introduce":[58],"SHREDBENCH,":[59],"benchmark":[61],"supported":[62],"by":[63,80],"an":[64],"automated":[65],"generation":[66],"pipeline":[67,76],"renders":[69],"fragmented":[70],"documents":[71],"directly":[72],"Markdown.The":[74],"proposed":[75],"ensures":[77],"validity":[79],"allowing":[81],"the":[82,130,152],"flexible":[83],"integration":[84],"latest":[86],"or":[87],"unseen":[88],"textual":[89],"sources":[90],"to":[91,157],"prevent":[92],"training":[93],"data":[94],"contamination.SHREDBENCH":[95],"assesses":[96],"four":[97],"scenarios":[98],"(English,":[99],"Chinese,":[100],"Code,":[101],"Table":[102],")":[103],"three":[105],"fragmentation":[106,144],"granularities":[107],"(8,":[108],"12,":[109],"16":[110],"pieces).Empirical":[111],"evaluations":[112],"state-of-the-art":[114],"MLLMs":[115,150],"reveal":[116],"gap:":[120],"The":[121],"method":[122],"is":[123,132],"effective":[124],"intact":[126],"documents;":[127],"however,":[128],"once":[129],"shredded,":[133],"becomes":[135],"challenge,":[138],"NED":[140],"dropping":[141],"sharply":[142],"as":[143],"increases.Our":[145],"findings":[146],"highlight":[147],"current":[149],"lack":[151],"fine-grained":[153],"crossmodal":[154],"required":[156],"bridge":[158],"discontinuities,":[160],"identifying":[161],"critical":[163],"gap":[164],"robust":[166],"research":[168],"1":[169],".":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}