{"id":"https://openalex.org/W4409403872","doi":"https://doi.org/10.1145/3711542.3711575","title":"Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data","display_name":"Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4409403872","doi":"https://doi.org/10.1145/3711542.3711575"},"language":"en","primary_location":{"id":"doi:10.1145/3711542.3711575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711575","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711575","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 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711575","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074491328","display_name":"Anum Afzal","orcid":"https://orcid.org/0000-0001-8146-1949"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210110383","display_name":"Universit\u00e4t Bayern","ror":"https://ror.org/01k8fm112","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210110383"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Anum Afzal","raw_affiliation_strings":["School of CIT, Technical University of Munich University, Munich, Bayern, Germany"],"affiliations":[{"raw_affiliation_string":"School of CIT, Technical University of Munich University, Munich, Bayern, Germany","institution_ids":["https://openalex.org/I4210110383","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072143812","display_name":"Juraj Vladika","orcid":"https://orcid.org/0000-0002-4941-9166"},"institutions":[{"id":"https://openalex.org/I4210110383","display_name":"Universit\u00e4t Bayern","ror":"https://ror.org/01k8fm112","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210110383"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Juraj Vladika","raw_affiliation_strings":["School of CIT, Technical University of Munich University, Munich, Bayern, Germany"],"affiliations":[{"raw_affiliation_string":"School of CIT, Technical University of Munich University, Munich, Bayern, Germany","institution_ids":["https://openalex.org/I4210110383","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114658599","display_name":"Gentrit Fazlija","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210110383","display_name":"Universit\u00e4t Bayern","ror":"https://ror.org/01k8fm112","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210110383"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gentrit Fazlija","raw_affiliation_strings":["School of CIT, Technical University of Munich University, Munich, Bayern, Germany"],"affiliations":[{"raw_affiliation_string":"School of CIT, Technical University of Munich University, Munich, Bayern, Germany","institution_ids":["https://openalex.org/I4210110383","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114658600","display_name":"Andrei Staradubets","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110383","display_name":"Universit\u00e4t Bayern","ror":"https://ror.org/01k8fm112","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210110383"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andrei Staradubets","raw_affiliation_strings":["School of CIT, Technical University of Munich University, Munich, Bayern, Germany"],"affiliations":[{"raw_affiliation_string":"School of CIT, Technical University of Munich University, Munich, Bayern, Germany","institution_ids":["https://openalex.org/I4210110383","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022973212","display_name":"Florian Matthes","orcid":"https://orcid.org/0000-0002-6667-5452"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210110383","display_name":"Universit\u00e4t Bayern","ror":"https://ror.org/01k8fm112","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210110383"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Matthes","raw_affiliation_strings":["School of CIT, Technical University of Munich University, Munich, Bayern, Germany"],"affiliations":[{"raw_affiliation_string":"School of CIT, Technical University of Munich University, Munich, Bayern, Germany","institution_ids":["https://openalex.org/I4210110383","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074491328"],"corresponding_institution_ids":["https://openalex.org/I4210110383","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":2.5398,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91225944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.7969719767570496},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5598275661468506},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5022273063659668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4851185083389282},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4563520550727844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44896793365478516},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3350197672843933},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.19675478339195251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969719767570496},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5598275661468506},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5022273063659668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4851185083389282},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4563520550727844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44896793365478516},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3350197672843933},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.19675478339195251}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711542.3711575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711575","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711575","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 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711542.3711575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711542.3711575","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711542.3711575","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 2024 8th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409403872.pdf","grobid_xml":"https://content.openalex.org/works/W4409403872.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2805159187","https://openalex.org/W2944145673","https://openalex.org/W2948335087","https://openalex.org/W2962985038","https://openalex.org/W3039946271","https://openalex.org/W3167554351","https://openalex.org/W3170033958","https://openalex.org/W3176913643","https://openalex.org/W3201077663","https://openalex.org/W4252076394","https://openalex.org/W4282824651","https://openalex.org/W4284670538","https://openalex.org/W4287887100","https://openalex.org/W4312443713","https://openalex.org/W4317898419","https://openalex.org/W4323655724","https://openalex.org/W4385565351","https://openalex.org/W4389518671","https://openalex.org/W4389519254","https://openalex.org/W4389519321","https://openalex.org/W4401042558"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W4231937131","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W1480341462","https://openalex.org/W598950423","https://openalex.org/W4256673449","https://openalex.org/W4292559016"],"abstract_inverted_index":{"Given":[0],"the":[1,40,45,68,75,81,85,106,126],"growing":[2],"trend":[3],"of":[4,77,87,110],"many":[5],"organizations":[6],"integrating":[7],"Retrieval":[8],"Augmented":[9],"Generation":[10],"(RAG)":[11],"into":[12,105],"their":[13],"operations,":[14],"we":[15,101],"assess":[16,74],"RAG":[17,69,82,111],"on":[18,49],"domain-specific":[19,114],"data":[20,50],"and":[21,36,42,93,96,108],"test":[22],"state-of-the-art":[23],"models":[24],"across":[25],"various":[26,54,78],"optimization":[27,109],"techniques.We":[28],"incorporate":[29],"four":[30],"optimizations;":[31],"Multi-Query,":[32],"Child-Parent-Retriever,":[33],"Ensemble":[34],"Retriever,":[35],"In-Context-Learning,":[37],"to":[38,73],"enhance":[39],"functionality":[41],"performance":[43,120],"in":[44,113,125],"academic":[46],"domain.We":[47],"focus":[48],"retrieval,":[51],"specifically":[52],"targeting":[53],"study":[55],"programs":[56],"at":[57],"a":[58,64,118],"large":[59],"technical":[60],"university.We":[61],"additionally":[62],"introduce":[63],"novel":[65],"evaluation":[66],"approach,":[67],"Confusion":[70],"Matrix":[71],"designed":[72],"effectiveness":[76],"configurations":[79],"within":[80],"framework.By":[83],"exploring":[84],"integration":[86],"both":[88],"open-source":[89],"(e.g.,":[90],"Llama2,":[91],"Mistral)":[92],"closed-source":[94],"(GPT-3.5":[95],"GPT-4)":[97],"Large":[98],"Language":[99],"Models,":[100],"offer":[102],"valuable":[103],"insights":[104],"application":[107],"frameworks":[112],"contexts.Our":[115],"experiments":[116],"show":[117],"significant":[119],"increase":[121],"when":[122],"including":[123],"multi-query":[124],"retrieval":[127],"phase.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}