{"id":"https://openalex.org/W7166879473","doi":"https://doi.org/10.18653/v1/2026.acl-industry.60","title":"When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation","display_name":"When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166879473","doi":"https://doi.org/10.18653/v1/2026.acl-industry.60"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-industry.60","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-industry.60","pdf_url":"https://aclanthology.org/2026.acl-industry.60.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-industry.60.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139797583","display_name":"Lin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Sun","raw_affiliation_strings":["Beijing Qiyuan Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Qiyuan Technology","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139805032","display_name":"Wangdexian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wangdexian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123926940","display_name":"Jingang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingang Huang","raw_affiliation_strings":["Beijing Qiyuan Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Qiyuan Technology","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123935202","display_name":"Linglin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linglin Zhang","raw_affiliation_strings":["Beijing Qiyuan Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Qiyuan Technology","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139749998","display_name":"Change Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Change Jia","raw_affiliation_strings":["Beijing Qiyuan Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Qiyuan Technology","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124049849","display_name":"Zhengwei Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengwei Cheng","raw_affiliation_strings":["Beijing Qiyuan Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Qiyuan Technology","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139804846","display_name":"Xiangzheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangzheng Zhang","raw_affiliation_strings":["Beijing Qiyuan Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Qiyuan Technology","institution_ids":["https://openalex.org/I4210115040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.88291849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"884","last_page":"894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.35089999437332153,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.35089999437332153,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0722000002861023,"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":0.06790000200271606,"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/benchmarking","display_name":"Benchmarking","score":0.7269999980926514},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7089999914169312},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.3666999936103821},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.31929999589920044},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2773999869823456}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7269999980926514},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7089999914169312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6800000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153999924659729},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.31929999589920044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.251800000667572},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-industry.60","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-industry.60","pdf_url":"https://aclanthology.org/2026.acl-industry.60.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-industry.60","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-industry.60","pdf_url":"https://aclanthology.org/2026.acl-industry.60.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166879473.pdf","grobid_xml":"https://content.openalex.org/works/W7166879473.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Lin":[0],"Sun,":[1],"Wangdexian,":[2],"Jingang":[3],"Huang,":[4],"Linglin":[5],"Zhang,":[6],"Change":[7],"Jia,":[8],"Zhengwei":[9],"Cheng,":[10],"Xiangzheng":[11],"Zhang.":[12],"Proceedings":[13],"of":[14,19],"the":[15,20],"64th":[16],"Annual":[17],"Meeting":[18],"Association":[21],"for":[22],"Computational":[23],"Linguistics":[24],"(Volume":[25],"6:":[26],"Industry":[27],"Track).":[28],"2026.":[29]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}