{"id":"https://openalex.org/W7066979709","doi":null,"title":"Leveraging Large Language Models (LLMs) for Automated Extraction and Processing of Complex Ordering Forms","display_name":"Leveraging Large Language Models (LLMs) for Automated Extraction and Processing of Complex Ordering Forms","publication_year":2024,"publication_date":"2024-05-01","ids":{"openalex":"https://openalex.org/W7066979709"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/156567","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/156567","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/156567/1/daqqah-bdaqqah-meng-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/156567/1/daqqah-bdaqqah-meng-eecs-2024-thesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Daqqah, Bilal H.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daqqah, Bilal H.","raw_affiliation_strings":["Computer Science and Engineering , Massachusetts Institute of Technology , 2023","MASTER OF ENGINEERING IN ELECTRICAL ENGINEERING AND COMPUTER SCIENCE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering , Massachusetts Institute of Technology , 2023","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MASTER OF ENGINEERING IN ELECTRICAL ENGINEERING AND COMPUTER SCIENCE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9692000150680542,"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":0.9692000150680542,"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/T10028","display_name":"Topic Modeling","score":0.02459999918937683,"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/T13287","display_name":"Robotic Process Automation Applications","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9380000233650208},{"id":"https://openalex.org/keywords/document-data-extraction","display_name":"document data extraction","score":0.7950000166893005},{"id":"https://openalex.org/keywords/procurement-documents","display_name":"procurement documents","score":0.9760000109672546},{"id":"https://openalex.org/keywords/page-classification","display_name":"page classification","score":0.6190000176429749},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.8740000128746033},{"id":"https://openalex.org/keywords/table-extraction","display_name":"table extraction","score":0.9950000047683716},{"id":"https://openalex.org/keywords/gpt-4-turbo","display_name":"GPT-4 Turbo","score":0.703000009059906},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.8140000104904175},{"id":"https://openalex.org/keywords/unstructured-documents","display_name":"unstructured documents","score":0.6050000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753999829292297},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4645000100135803},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C46934059","wikidata":"https://www.wikidata.org/wiki/Q61515","display_name":"Outsourcing","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4228000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090999960899353},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39250001311302185},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.3319000005722046},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C201650216","wikidata":"https://www.wikidata.org/wiki/Q829492","display_name":"Procurement","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2983335612","wikidata":"https://www.wikidata.org/wiki/Q54277","display_name":"Word processing","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/156567","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/156567","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/156567/1/daqqah-bdaqqah-meng-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/156567","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/156567","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/156567/1/daqqah-bdaqqah-meng-eecs-2024-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"},{"id":"https://openalex.org/F4320334266","display_name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology","ror":"https://ror.org/01e85r662"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7066979709.pdf","grobid_xml":"https://content.openalex.org/works/W7066979709.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2626778328","https://openalex.org/W2952895179","https://openalex.org/W2964346820","https://openalex.org/W2981852735","https://openalex.org/W2997154779","https://openalex.org/W3030163527","https://openalex.org/W3113463745","https://openalex.org/W3152774549","https://openalex.org/W3168867926","https://openalex.org/W3198963017","https://openalex.org/W3212748493","https://openalex.org/W4283026156","https://openalex.org/W4304013646","https://openalex.org/W4306707571","https://openalex.org/W4308900200","https://openalex.org/W4313163001","https://openalex.org/W4327810158","https://openalex.org/W4383604278","https://openalex.org/W4385990942","https://openalex.org/W4386907142","https://openalex.org/W4386942705","https://openalex.org/W4387074826","https://openalex.org/W4402671775","https://openalex.org/W4402684297","https://openalex.org/W4402702988","https://openalex.org/W4404356490","https://openalex.org/W4404782801","https://openalex.org/W4410202262"],"related_works":["https://openalex.org/W4404166038","https://openalex.org/W4402335804","https://openalex.org/W4415524164","https://openalex.org/W7133539559","https://openalex.org/W7138936582","https://openalex.org/W7014994763","https://openalex.org/W7165498877","https://openalex.org/W7128814598","https://openalex.org/W4410721853","https://openalex.org/W7212287555"],"abstract_inverted_index":{"Data":[0],"extraction":[1,59,115],"from":[2,16],"business":[3,180],"documents":[4,67,73],"is":[5],"a":[6,130],"critical":[7],"but":[8],"under-exploited":[9],"area":[10],"capable":[11],"of":[12,51,62,88,165],"unlocking":[13],"significant":[14],"value":[15],"vast":[17],"document":[18,169],"archives.":[19],"Traditional":[20],"methods":[21],"relying":[22],"on":[23],"manual":[24],"intervention":[25],"or":[26],"outsourcing":[27],"are":[28],"inefficient,":[29],"error-prone,":[30],"and":[31,33,37,60,65,86,102,107,129,158,178],"costly,":[32],"commercial":[34],"Deep":[35],"Learning-based":[36],"OCR":[38,101],"solutions":[39],"still":[40],"struggle":[41],"with":[42,70,120,126,149],"highly":[43],"unstructured":[44],"documents.":[45],"This":[46,160],"thesis":[47],"explores":[48],"the":[49,58,84,136,163,173],"use":[50],"Large":[52],"Language":[53],"Models":[54],"(LLMs)":[55],"to":[56,167],"automate":[57],"processing":[61,170],"ordering":[63],"forms":[64],"procurement":[66],"in":[68,78,134],"collaboration":[69],"SiliconExperts.":[71],"These":[72],"contain":[74],"complex":[75],"codes":[76],"used":[77],"electronic":[79],"component":[80],"procurement,":[81],"which":[82,135],"guide":[83],"manufacture":[85],"specification":[87],"parts.":[89],"We":[90],"developed":[91],"an":[92],"end-to-end":[93],"pipeline":[94,143],"comprising":[95],"four":[96],"key":[97],"modules:":[98],"Page":[99],"Classification,":[100],"Table":[103],"Extraction,":[104],"LLM":[105],"Inference,":[106],"Code":[108],"Combination":[109],"Generation.":[110],"Two":[111],"approaches":[112],"for":[113],"key-value":[114],"were":[116],"compared:":[117],"one-shot":[118],"prompting":[119],"in-context":[121],"learning":[122],"using":[123],"GPT-4":[124],"Turbo":[125],"Vision":[127],"(GPT-4V)":[128],"fine-tuned":[131],"GPT-3.5":[132],"model,":[133],"GPT-4V":[137],"approach":[138],"demonstrated":[139],"superior":[140],"performance.":[141,159],"The":[142],"effectively":[144],"generated":[145],"correct":[146],"code":[147],"combinations":[148],"high":[150],"accuracy,":[151],"although":[152],"data":[153],"quality":[154],"issues":[155],"impacted":[156],"precision":[157],"research":[161],"highlights":[162],"potential":[164],"LLMs":[166],"transform":[168],"workflows,":[171],"bridging":[172],"gap":[174],"between":[175],"academic":[176],"advancements":[177],"practical":[179],"applications.":[181]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}