{"id":"https://openalex.org/W6906869370","doi":"https://doi.org/10.18420/inf2024_120","title":"Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5","display_name":"Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6906869370","doi":"https://doi.org/10.18420/inf2024_120"},"language":"en","primary_location":{"id":"doi:10.18420/inf2024_120","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_120","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/inf2024_120","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lamott, Marcel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lamott, Marcel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shakir, Muhammad Armaghan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shakir, Muhammad Armaghan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69894141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10028","display_name":"Topic Modeling","score":0.3149000108242035,"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/T10028","display_name":"Topic Modeling","score":0.3149000108242035,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0771000012755394,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.05640000104904175,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5016000270843506},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.49720001220703125},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44429999589920044},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/realm","display_name":"Realm","score":0.35740000009536743},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.35690000653266907},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.3449000120162964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737500011920929},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C2778757428","wikidata":"https://www.wikidata.org/wiki/Q1250464","display_name":"Realm","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3449000120162964},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C2777083192","wikidata":"https://www.wikidata.org/wiki/Q1814648","display_name":"Plain language","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/inf2024_120","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_120","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/inf2024_120","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_120","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"score":0.713100254535675,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"surge":[1],"of":[2,23,55,94,104,148,172,179],"digital":[3],"documents":[4,11],"in":[5,57,175,183,189],"various":[6],"formats,":[7],"including":[8],"less":[9],"standardized":[10],"such":[12],"as":[13],"business":[14],"reports":[15],"and":[16,134,164,193],"environmental":[17],"assessments,":[18],"underscores":[19],"the":[20,53,92,102,124,146,159,170,177],"growing":[21],"importance":[22],"Document":[24,44],"Understanding.":[25],"While":[26],"Large":[27],"Language":[28],"Models":[29],"(LLMs)":[30],"have":[31],"showcased":[32],"prowess":[33],"across":[34],"diverse":[35],"natural":[36,190],"language":[37,181,191],"processing":[38,192],"tasks,":[39],"their":[40,61,77],"direct":[41],"application":[42],"to":[43,68,83,100,137,145],"Understanding":[45],"remains":[46],"a":[47,81,114,154],"challenge.":[48],"Previous":[49],"research":[50],"has":[51],"demonstrated":[52],"utility":[54],"LLMs":[56,74,106,163],"this":[58,87],"domain,":[59],"yet":[60],"significant":[62],"computational":[63,109],"demands":[64],"make":[65],"them":[66],"challenging":[67],"deploy":[69],"effectively.":[70],"Additionally,":[71],"proprietary":[72,125],"Blackbox":[73],"often":[75],"outperform":[76],"open-source":[78],"counterparts,":[79],"posing":[80],"barrier":[82],"widespread":[84],"accessibility.":[85],"In":[86],"paper,":[88],"we":[89,112,118],"delve":[90],"into":[91,128],"realm":[93],"document":[95,120,149,194],"understanding,":[96],"leveraging":[97],"distillation":[98,173],"methods":[99],"harness":[101],"power":[103],"large":[105],"while":[107],"accommodating":[108],"limitations.":[110],"Specifically,":[111],"present":[113],"novel":[115],"approach":[116],"wherein":[117],"distill":[119],"understanding":[121,150],"knowledge":[122,140],"from":[123],"LLM":[126],"ChatGPT":[127],"FLAN-T5.":[129],"Our":[130,167],"methodology":[131],"integrates":[132],"labeling":[133],"curriculum-learning":[135],"mechanisms":[136],"facilitate":[138],"efficient":[139],"transfer.":[141],"This":[142],"work":[143],"contributes":[144],"advancement":[147],"methodologies":[151],"by":[152],"offering":[153],"scalable":[155],"solution":[156],"that":[157],"bridges":[158],"gap":[160],"between":[161],"resource-intensive":[162],"practical":[165],"applications.":[166],"findings":[168],"underscore":[169],"potential":[171],"techniques":[174],"facilitating":[176],"deployment":[178],"sophisticated":[180],"models":[182],"real-world":[184],"scenarios,":[185],"thereby":[186],"fostering":[187],"advancements":[188],"comprehension":[195],"domains.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}