{"id":"https://openalex.org/W4416035437","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1585","title":"DELOC: Document Element Localizer","display_name":"DELOC: Document Element Localizer","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035437","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1585"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1585","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1585","pdf_url":"https://aclanthology.org/2025.emnlp-main.1585.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1585.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040649771","display_name":"Hammad A. Ayyubi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hammad Ayyubi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050532692","display_name":"Puneet Mathur","orcid":"https://orcid.org/0000-0002-8458-1476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puneet Mathur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115560745","display_name":"Mehrab Tanjim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehrab Tanjim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038267072","display_name":"Vlad I. Morariu","orcid":"https://orcid.org/0000-0001-7937-7748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vlad I Morariu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040649771"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35161486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31126","last_page":"31135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.13339999318122864,"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":0.13339999318122864,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.048900000751018524,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.04879999905824661,"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/executable","display_name":"Executable","score":0.761900007724762},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6140000224113464},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5200999975204468},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.51910001039505},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5164999961853027},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49480000138282776},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.36570000648498535},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.35589998960494995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670999765396118},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.761900007724762},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6140000224113464},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1585","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1585","pdf_url":"https://aclanthology.org/2025.emnlp-main.1585.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1585","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1585","pdf_url":"https://aclanthology.org/2025.emnlp-main.1585.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035437.pdf","grobid_xml":"https://content.openalex.org/works/W4416035437.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Editing":[0],"documents":[1],"and":[2,21,36,45,129],"PDFs":[3],"using":[4,142],"natural":[5,109],"language":[6],"instructions":[7],"is":[8,76,149],"desirable":[9],"for":[10,22],"many":[11],"reasons":[12],"-ease":[13],"of":[14,101,147],"use,":[15],"increasing":[16],"accessibility":[17],"to":[18,30,39,50,60,79,111,139],"non-technical":[19],"users,":[20],"creativity.To":[23],"do":[24],"this":[25,38,87],"automatically,":[26],"a":[27,70],"system":[28,48],"needs":[29,49],"first":[31],"understand":[32],"the":[33,47,54,57,77,81,98,152,159],"user's":[34],"intent":[35],"convert":[37],"an":[40,136],"executable":[41],"plan":[42],"or":[43,52],"command,":[44],"then":[46],"identify":[51],"localize":[53],"elements":[55],"that":[56,65],"user":[58],"desires":[59],"edit.While":[61],"there":[62],"exist":[63],"methods":[64],"can":[66],"accomplish":[67],"these":[68,74],"tasks,":[69],"major":[71],"bottleneck":[72],"in":[73,151],"systems":[75],"inability":[78],"ground":[80],"spatial":[82],"edit":[83],"location":[84],"effectively.We":[85],"address":[86],"gap":[88],"through":[89],"our":[90],"proposed":[91],"system,":[92],"DELOC":[93,148],"(Document":[94],"Element":[95],"LOCalizer).DELOC":[96],"adapts":[97],"grounding":[99],"capabilities":[100],"existing":[102],"Multimodal":[103],"Large":[104],"Language":[105],"Model":[106],"(MLLM)":[107],"from":[108,125],"images":[110],"PDFs.This":[112],"adaptation":[113],"involves":[114],"two":[115],"novel":[116],"contributions:":[117],"1)":[118],"synthetically":[119],"generating":[120],"PDF-grounding":[121],"instruction":[122],"tuning":[123],"data":[124,132,141],"partially":[126],"annotated":[127],"datasets;":[128],"2)":[130],"synthetic":[131],"cleaning":[133],"via":[134],"Code-NLI,":[135],"NLI-inspired":[137],"process":[138],"clean":[140],"generated":[143],"Python":[144],"code.The":[145],"effectiveness":[146],"apparent":[150],">2x":[153],"zeroshot":[154],"improvement":[155],"it":[156],"achieves":[157],"over":[158],"next":[160],"best":[161],"MLLM,":[162],"GPT-4o.":[163]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}