{"id":"https://openalex.org/W7130533523","doi":"https://doi.org/10.1109/fllm67465.2025.11390895","title":"GPT-2++: An Optimized GPT-2 for RAG by Integrating BERT, Prompt Engineering, and Fine-Tuning","display_name":"GPT-2++: An Optimized GPT-2 for RAG by Integrating BERT, Prompt Engineering, and Fine-Tuning","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W7130533523","doi":"https://doi.org/10.1109/fllm67465.2025.11390895"},"language":null,"primary_location":{"id":"doi:10.1109/fllm67465.2025.11390895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11390895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022547940","display_name":"Fadi Yamout","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104393","display_name":"International University of Beirut","ror":"https://ror.org/01fjkp854","country_code":"LB","type":"education","lineage":["https://openalex.org/I4210104393"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Fadi Yamout","raw_affiliation_strings":["International University of Beirut,Department of Computer Science,Beirut,Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International University of Beirut,Department of Computer Science,Beirut,Lebanon","institution_ids":["https://openalex.org/I4210104393"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126367054","display_name":"Hasan Aboul Hasan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104393","display_name":"International University of Beirut","ror":"https://ror.org/01fjkp854","country_code":"LB","type":"education","lineage":["https://openalex.org/I4210104393"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Hasan Aboul Hasan","raw_affiliation_strings":["International University of Beirut,Department of Computer Science,Beirut,Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International University of Beirut,Department of Computer Science,Beirut,Lebanon","institution_ids":["https://openalex.org/I4210104393"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81663628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6991999745368958,"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":0.6991999745368958,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.048500001430511475,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.043299999088048935,"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/key","display_name":"Key (lock)","score":0.7135999798774719},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48559999465942383},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.3589000105857849},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.34540000557899475},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3425000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197000026702881},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7135999798774719},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm67465.2025.11390895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm67465.2025.11390895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41940629482269287,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2760656271","https://openalex.org/W2979826702","https://openalex.org/W4309674289","https://openalex.org/W4385245566","https://openalex.org/W4416310693"],"related_works":[],"abstract_inverted_index":{"Retrieval":[0],"Augmented":[1],"Generation":[2],"(RAG)":[3],"systems":[4],"enhance":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"by":[10],"allowing":[11],"them":[12],"to":[13,68,82,105],"answer":[14,137,143],"questions":[15],"from":[16],"specific":[17],"knowledge":[18],"sources,":[19],"thereby":[20],"reducing":[21],"hallucinations":[22],"and":[23,32,160,181],"improving":[24],"factual":[25],"accuracy.":[26],"While":[27],"powerful":[28],"models":[29,56],"like":[30,57],"GPT-3":[31],"GPT-4":[33,163],"excel":[34],"in":[35,72,177],"RAG":[36,73,196],"frameworks,":[37],"their":[38,43],"high":[39],"computational":[40],"requirements":[41],"preclude":[42],"use":[44],"on":[45,100],"resource-constrained":[46],"hardware,":[47],"such":[48,63],"as":[49,164,190],"Internet":[50],"of":[51,179],"Things":[52],"(IoT)":[53],"devices.":[54],"Smaller":[55],"GPT-2":[58,99,159,176],"are":[59],"more":[60,113],"suitable":[61],"for":[62,88,134,194],"environments":[64],"but":[65],"typically":[66],"struggle":[67],"produce":[69],"meaningful":[70],"output":[71],"tasks.":[74],"This":[75],"paper":[76],"proposes":[77],"GPT-2++,":[78,123],"a":[79,101,120,128,141,149,191],"novel":[80],"framework":[81],"significantly":[83],"improve":[84],"GPT-2's":[85],"question-answering":[86],"capabilities":[87],"RAG.":[89],"Our":[90],"approach":[91],"involves":[92],"two":[93],"key":[94],"contributions:":[95],"first,":[96],"we":[97,118],"fine-tune":[98],"custom-built,":[102],"high-quality":[103],"dataset":[104],"create":[106],"an":[107,165],"optimized":[108],"model,":[109],"GPT-2-FT,":[110],"which":[111],"generates":[112],"contextually":[114],"relevant":[115],"answers.":[116],"Second,":[117],"introduce":[119],"dual-model":[121],"architecture,":[122],"that":[124,144,171],"integrates":[125],"GPT-2-FT":[126,145],"with":[127,185],"BERT":[129,131],"model.":[130],"is":[132],"leveraged":[133],"its":[135,188],"superior":[136],"extraction":[138],"capabilities,":[139],"providing":[140],"concise":[142],"then":[146],"expands":[147],"into":[148],"comprehensive,":[150],"human-readable":[151],"response.":[152],"We":[153],"evaluate":[154],"GPT-2++":[155,172],"against":[156],"the":[157,174],"original":[158],"GPT-3.5,":[161,186],"using":[162],"impartial":[166],"evaluator.":[167],"The":[168],"results":[169],"demonstrate":[170],"outperforms":[173],"base":[175],"90.6%":[178],"cases":[180],"shows":[182],"competitive":[183],"performance":[184],"validating":[187],"efficacy":[189],"resource-efficient":[192],"solution":[193],"advanced":[195],"systems.":[197]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-20T00:00:00"}