{"id":"https://openalex.org/W4417068614","doi":"https://doi.org/10.48550/arxiv.2503.23013","title":"DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation","display_name":"DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-03-29","ids":{"openalex":"https://openalex.org/W4417068614","doi":"https://doi.org/10.48550/arxiv.2503.23013"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.23013","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23013","pdf_url":"https://arxiv.org/pdf/2503.23013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.23013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hsu, Hsin-Ling","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsu, Hsin-Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120751839","display_name":"Jengnan Tzeng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tzeng, Jengnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6342999935150146,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6342999935150146,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.357699990272522,"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":0.0008999999845400453,"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/hybrid-search","display_name":"hybrid retrieval","score":0.828000009059906},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9900000095367432},{"id":"https://openalex.org/keywords/dense-retrieval","display_name":"dense retrieval","score":0.7450000047683716},{"id":"https://openalex.org/keywords/bm25","display_name":"BM25","score":0.9549999833106995},{"id":"https://openalex.org/keywords/dynamic-weighting","display_name":"dynamic weighting","score":0.6290000081062317},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7429999709129333},{"id":"https://openalex.org/keywords/retrieval-effectiveness-evaluation","display_name":"retrieval effectiveness evaluation","score":0.4350000023841858}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8317999839782715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715399980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.23013","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23013","pdf_url":"https://arxiv.org/pdf/2503.23013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.23013","doi":"https://doi.org/10.48550/arxiv.2503.23013","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.23013","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.23013","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.23013","pdf_url":"https://arxiv.org/pdf/2503.23013","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hybrid":[0],"retrieval":[1,10,18,48,54,77,117],"techniques":[2],"in":[3],"Retrieval-Augmented":[4],"Generation":[5],"(RAG)":[6],"systems":[7],"enhance":[8],"information":[9],"by":[11],"combining":[12],"dense":[13,53],"and":[14,55,100,134],"sparse":[15],"(e.g.,":[16],"BM25-based)":[17],"methods.":[19],"However,":[20],"existing":[21],"approaches":[22],"struggle":[23],"with":[24],"adaptability,":[25],"as":[26],"fixed":[27],"weighting":[28,90,102],"schemes":[29],"fail":[30],"to":[31,33,67,83],"adjust":[32],"different":[34],"queries.":[35],"To":[36],"address":[37],"this,":[38],"we":[39],"propose":[40],"DAT":[41,60,111,127],"(Dynamic":[42],"Alpha":[43],"Tuning),":[44],"a":[45,62,97],"novel":[46],"hybrid":[47,116],"framework":[49],"that":[50,110],"dynamically":[51],"balances":[52],"BM25":[56],"for":[57],"each":[58],"query.":[59],"leverages":[61],"large":[63],"language":[64],"model":[65],"(LLM)":[66],"evaluate":[68],"the":[69,72,88,104],"effectiveness":[70,81,93],"of":[71],"top-1":[73],"results":[74,108],"from":[75],"both":[76],"methods,":[78],"assigning":[79],"an":[80],"score":[82,94],"each.":[84],"It":[85],"then":[86],"calibrates":[87],"optimal":[89],"factor":[91],"through":[92],"normalization,":[95],"ensuring":[96],"more":[98],"adaptive":[99],"query-aware":[101],"between":[103],"two":[105],"approaches.":[106],"Empirical":[107],"show":[109],"consistently":[112],"significantly":[113],"outperforms":[114],"fixed-weighting":[115],"methods":[118],"across":[119],"various":[120],"evaluation":[121],"metrics.":[122],"Even":[123],"on":[124],"smaller":[125],"models,":[126],"delivers":[128],"strong":[129],"performance,":[130],"highlighting":[131],"its":[132],"efficiency":[133],"adaptability.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}