{"id":"https://openalex.org/W4412888667","doi":"https://doi.org/10.18653/v1/2025.findings-acl.379","title":"A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding","display_name":"A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888667","doi":"https://doi.org/10.18653/v1/2025.findings-acl.379"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.379","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.379","pdf_url":"https://aclanthology.org/2025.findings-acl.379.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 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.379.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050212540","display_name":"Jinghui Lu","orcid":"https://orcid.org/0000-0001-7149-6961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinghui Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101650550","display_name":"Haiyang Yu","orcid":"https://orcid.org/0000-0001-9311-0230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyang Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738102","display_name":"Yanjie Wang","orcid":"https://orcid.org/0000-0002-2305-1041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanjie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103248206","display_name":"Yongjie Ye","orcid":"https://orcid.org/0009-0000-0093-7993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongjie Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681719","display_name":"Jingqun Tang","orcid":"https://orcid.org/0000-0003-2577-0119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingqun Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070359048","display_name":"Ziwei Yang","orcid":"https://orcid.org/0000-0001-9846-840X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziwei Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036758849","display_name":"Binghong Wu","orcid":"https://orcid.org/0000-0002-3361-2260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binghong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393403","display_name":"Qi Liu","orcid":"https://orcid.org/0009-0000-4144-938X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005177314","display_name":"Hao Feng","orcid":"https://orcid.org/0000-0002-0899-0438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452675","display_name":"Han Wang","orcid":"https://orcid.org/0000-0002-1320-0947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458818","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0002-5248-935X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102003518","display_name":"Can Huang","orcid":"https://orcid.org/0009-0006-9126-3069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Can Huang","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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7252","last_page":"7273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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":0.9948999881744385,"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":0.9930999875068665,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9663000106811523,"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/computer-science","display_name":"Computer science","score":0.8229495286941528},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.8215130567550659},{"id":"https://openalex.org/keywords/interleaving","display_name":"Interleaving","score":0.7377058267593384},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6368382573127747},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5986855030059814},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.43207743763923645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3586632013320923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3142091631889343},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1809886395931244},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17077767848968506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229495286941528},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8215130567550659},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.7377058267593384},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6368382573127747},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5986855030059814},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.43207743763923645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3586632013320923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3142091631889343},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1809886395931244},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17077767848968506},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.379","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.379","pdf_url":"https://aclanthology.org/2025.findings-acl.379.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.379","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.379","pdf_url":"https://aclanthology.org/2025.findings-acl.379.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888667.pdf","grobid_xml":"https://content.openalex.org/works/W4412888667.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W4287027631","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Jinghui":[0],"Lu,":[1],"Haiyang":[2],"Yu,":[3],"Yanjie":[4],"Wang,":[5,19],"Yongjie":[6],"Ye,":[7],"Jingqun":[8],"Tang,":[9],"Ziwei":[10],"Yang,":[11],"Binghong":[12],"Wu,":[13],"Qi":[14],"Liu,":[15,21],"Hao":[16,20],"Feng,":[17],"Han":[18],"Can":[22],"Huang.":[23],"Findings":[24],"of":[25],"the":[26],"Association":[27],"for":[28],"Computational":[29],"Linguistics:":[30],"ACL":[31],"2025.":[32,33]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
