{"id":"https://openalex.org/W7119908673","doi":"https://doi.org/10.48550/arxiv.2601.04646","title":"Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search","display_name":"Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search","publication_year":2026,"publication_date":"2026-01-08","ids":{"openalex":"https://openalex.org/W7119908673","doi":"https://doi.org/10.48550/arxiv.2601.04646"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.04646","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.04646","pdf_url":"https://arxiv.org/pdf/2601.04646","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2601.04646","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122563752","display_name":"Prateek Jain","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jain, Prateek","raw_affiliation_strings":["DevRev , Austin , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DevRev , Austin , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041867260","display_name":"Shabari S Nair","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nair, Shabari S","raw_affiliation_strings":["The University of Texas at Austin , Austin , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin , Austin , USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006663115","display_name":"Ritesh Goru","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goru, Ritesh","raw_affiliation_strings":["DevRev , Austin , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DevRev , Austin , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122432723","display_name":"Prakhar Agarwal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Prakhar","raw_affiliation_strings":["DevRev , Bengaluru , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DevRev , Bengaluru , India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122526425","display_name":"Ajay Yadav","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yadav, Ajay","raw_affiliation_strings":["The University of Texas at Austin , Austin , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin , Austin , USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122464336","display_name":"Yoga Sri Varshan Varadharajan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varadharajan, Yoga Sri Varshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053978837","display_name":"Constantine Caramanis","orcid":"https://orcid.org/0000-0001-9939-8378","observed_orcids":["https://orcid.org/0000-0001-9939-8378"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caramanis, Constantine","raw_affiliation_strings":["The University of Texas at Austin , Austin , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin , Austin , USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.9911999702453613,"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":0.9911999702453613,"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":0.006800000090152025,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0003000000142492354,"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/dark-data","display_name":"dark data","score":0.6610000133514404},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.890999972820282},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.7210000157356262},{"id":"https://openalex.org/keywords/query-logs","display_name":"query logs","score":0.38999998569488525},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313999772071838},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6879000067710876},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6186000108718872},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5824000239372253},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45170000195503235},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.29919999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.2770000100135803},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.260699987411499}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.04646","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.04646","pdf_url":"https://arxiv.org/pdf/2601.04646","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.04646","doi":"https://doi.org/10.48550/arxiv.2601.04646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04646","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.04646","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.04646","pdf_url":"https://arxiv.org/pdf/2601.04646","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7119908673.pdf","grobid_xml":"https://content.openalex.org/works/W7119908673.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214376720","https://openalex.org/W7128616383","https://openalex.org/W7151516777","https://openalex.org/W7138879855","https://openalex.org/W7208524746","https://openalex.org/W4416188982","https://openalex.org/W7127344497","https://openalex.org/W7204216673","https://openalex.org/W4416149454","https://openalex.org/W7167942765"],"abstract_inverted_index":{"Large-scale":[0],"multi-tenant":[1,49,138],"retrieval":[2,61],"systems":[3],"generate":[4],"extensive":[5],"query":[6,37,126],"logs":[7],"but":[8],"lack":[9],"curated":[10],"relevance":[11,91],"labels":[12],"for":[13,63,87],"effective":[14],"domain":[15],"adaptation,":[16],"resulting":[17],"in":[18,48],"substantial":[19],"underutilized":[20],"\"dark":[21],"data.\"":[22],"This":[23],"challenge":[24],"is":[25,46],"compounded":[26],"by":[27,84],"the":[28,106,110,125],"high":[29],"cost":[30],"of":[31,53,124],"model":[32],"updates,":[33],"as":[34],"jointly":[35],"fine-tuning":[36,123],"and":[38,80,90,96,118,135],"document":[39,111],"encoders":[40],"requires":[41],"full":[42],"corpus":[43],"re-indexing,":[44],"which":[45],"impractical":[47],"settings":[50],"with":[51],"thousands":[52],"isolated":[54],"indices.":[55],"We":[56,93],"introduce":[57],"DevRev-Search,":[58,116],"a":[59,69,129],"passage":[60],"benchmark":[62],"technical":[64],"customer":[65],"support":[66],"built":[67],"via":[68],"fully":[70],"automated":[71],"pipeline.":[72],"Candidate":[73],"generation":[74],"uses":[75],"fusion":[76],"across":[77],"diverse":[78],"sparse":[79],"dense":[81],"retrievers,":[82],"followed":[83],"an":[85],"LLM-as-a-Judge":[86],"consistency":[88],"filtering":[89],"labeling.":[92],"further":[94],"study":[95],"systematically":[97],"evaluate":[98],"index-preserving":[99],"query-only":[100],"adaptation":[101],"strategies":[102],"that":[103,121],"fine-tune":[104],"only":[105],"query-encoder":[107],"while":[108],"keeping":[109],"indices":[112],"fixed.":[113],"Experiments":[114],"on":[115],"SciFact,":[117],"FiQA-2018":[119],"show":[120],"parameter-efficient":[122],"encoder":[127],"delivers":[128],"remarkable":[130],"quality-efficiency":[131],"trade-off,":[132],"enabling":[133],"scalable":[134],"practical":[136],"enterprise":[137],"retrieval.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-01-10T00:00:00"}