{"id":"https://openalex.org/W4406459668","doi":"https://doi.org/10.1109/bigdata62323.2024.10825576","title":"Evaluation and Comparison of Open-Source LLMs Using Natural Language Generation Quality Metrics","display_name":"Evaluation and Comparison of Open-Source LLMs Using Natural Language Generation Quality Metrics","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459668","doi":"https://doi.org/10.1109/bigdata62323.2024.10825576"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5115904808","display_name":"Dzenan Hamzic","orcid":null},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Dzenan Hamzic","raw_affiliation_strings":["AIT Austrian Institute of Technology,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology,Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029942543","display_name":"Markus Wurzenberger","orcid":"https://orcid.org/0000-0003-3259-6972"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Markus Wurzenberger","raw_affiliation_strings":["AIT Austrian Institute of Technology,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology,Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088439816","display_name":"Florian Skopik","orcid":"https://orcid.org/0000-0002-1922-7892"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Florian Skopik","raw_affiliation_strings":["AIT Austrian Institute of Technology,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology,Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072210863","display_name":"Max Landauer","orcid":"https://orcid.org/0000-0003-3813-3151"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Max Landauer","raw_affiliation_strings":["AIT Austrian Institute of Technology,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology,Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057690103","display_name":"Andreas Rauber","orcid":"https://orcid.org/0000-0002-9272-6225"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andreas Rauber","raw_affiliation_strings":["TU Wien,Vienna,Austria"],"affiliations":[{"raw_affiliation_string":"TU Wien,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5115904808"],"corresponding_institution_ids":["https://openalex.org/I132118926"],"apc_list":null,"apc_paid":null,"fwci":2.1039,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89564573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5342","last_page":"5351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9955000281333923,"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":0.9914000034332275,"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/quality","display_name":"Quality (philosophy)","score":0.6469515562057495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.630174994468689},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5257692933082581},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4884130358695984},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41875356435775757},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3640426993370056},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.12094715237617493}],"concepts":[{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6469515562057495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.630174994468689},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5257692933082581},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4884130358695984},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41875356435775757},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3640426993370056},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.12094715237617493},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2108325777","https://openalex.org/W2970641574","https://openalex.org/W3027879771","https://openalex.org/W3034238904","https://openalex.org/W3035507081","https://openalex.org/W3099655892","https://openalex.org/W3133702157","https://openalex.org/W3134642945","https://openalex.org/W3169283738","https://openalex.org/W3195577433","https://openalex.org/W4224308101","https://openalex.org/W4285245049","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4378908626","https://openalex.org/W4380353763","https://openalex.org/W4384389802","https://openalex.org/W4384918448","https://openalex.org/W4385468994","https://openalex.org/W4385571157","https://openalex.org/W4387156782","https://openalex.org/W4387947619","https://openalex.org/W4388718089","https://openalex.org/W4391556020","https://openalex.org/W4393147129","https://openalex.org/W4393734619","https://openalex.org/W4396913672","https://openalex.org/W4399404161","https://openalex.org/W4403753183","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W6769627184","https://openalex.org/W6769652383","https://openalex.org/W6777615688","https://openalex.org/W6778883912","https://openalex.org/W6783672905","https://openalex.org/W6791376898","https://openalex.org/W6800751262","https://openalex.org/W6810081322","https://openalex.org/W6810730852","https://openalex.org/W6810792567","https://openalex.org/W6852874933","https://openalex.org/W6854475153","https://openalex.org/W6854866820","https://openalex.org/W6857079699","https://openalex.org/W6857956391","https://openalex.org/W6858104374","https://openalex.org/W6860710830","https://openalex.org/W6861697672","https://openalex.org/W6863578804","https://openalex.org/W6866906737","https://openalex.org/W6868863601","https://openalex.org/W6873764211","https://openalex.org/W6898505805","https://openalex.org/W7073593060"],"related_works":["https://openalex.org/W2955859849","https://openalex.org/W2122804826","https://openalex.org/W2152921782","https://openalex.org/W382594479","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2151245229","https://openalex.org/W2140902089","https://openalex.org/W2988746243","https://openalex.org/W1510553545"],"abstract_inverted_index":{"The":[0,69],"rapid":[1],"advancement":[2],"of":[3,38,54,103],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"has":[8],"transformed":[9],"natural":[10,143],"language":[11,144],"processing,":[12],"yet":[13],"comprehensive":[14,122],"evaluation":[15,45,123],"methods":[16],"are":[17],"necessary":[18],"to":[19,32,77,116],"ensure":[20],"their":[21,79],"reliability,":[22],"particularly":[23],"in":[24,94,127,142],"Retrieval-Augmented":[25],"Generation":[26],"(RAG)":[27],"tasks.":[28],"This":[29,113],"study":[30],"aims":[31],"evaluate":[33],"and":[34,64,90,100,146],"compare":[35],"the":[36,117,129],"performance":[37],"open-source":[39],"LLMs":[40,50,132],"by":[41,119],"introducing":[42],"a":[43,52,65,121],"rigorous":[44],"framework.":[46],"We":[47],"benchmark":[48],"20":[49],"using":[51],"combination":[53],"established":[55],"metrics":[56],"such":[57],"as":[58],"BLEU,":[59],"ROUGE,":[60],"BERTScore,":[61],"along":[62],"with":[63,137],"novel":[66],"metric,":[67],"RAGAS.":[68],"models":[70,87,108],"were":[71],"tested":[72],"across":[73],"two":[74],"distinct":[75],"datasets":[76],"assess":[78],"text":[80],"generation":[81],"quality.":[82],"Our":[83],"findings":[84],"reveal":[85],"that":[86,125],"like":[88],"nous-hermes-2-solar-10.7b":[89],"mistral-7b-instruct-v0.1":[91],"consistently":[92],"excel":[93],"tasks":[95],"requiring":[96],"strict":[97],"instruction":[98],"adherence":[99],"effective":[101],"use":[102],"large":[104],"contexts,":[105],"while":[106],"other":[107],"show":[109],"areas":[110],"for":[111,133,139],"improvement.":[112],"research":[114],"contributes":[115],"field":[118],"offering":[120],"framework":[124],"aids":[126],"selecting":[128],"most":[130],"suitable":[131],"complex":[134],"RAG":[135],"applications,":[136],"implications":[138],"future":[140],"developments":[141],"processing":[145],"big":[147],"data":[148],"analysis.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}
