{"id":"https://openalex.org/W7167943452","doi":"https://doi.org/10.1145/3805712.3809869","title":"LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum","display_name":"LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167943452","doi":"https://doi.org/10.1145/3805712.3809869"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809869","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809869","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036683049","display_name":"Zhichao Xu","orcid":"https://orcid.org/0000-0002-2370-4487"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhichao Xu","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0000-0002-2370-4487","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012958162","display_name":"Shengyao Zhuang","orcid":"https://orcid.org/0000-0002-6711-0955"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shengyao Zhuang","raw_affiliation_strings":["The University of Queensland, Brisbane, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6711-0955","affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390744","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0009-0009-0756-8110"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Crystina Zhang","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0009-0756-8110","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021623012","display_name":"Xueguang Ma","orcid":"https://orcid.org/0000-0003-3430-4910"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xueguang Ma","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3430-4910","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057838053","display_name":"Yijun Tian","orcid":"https://orcid.org/0000-0003-2795-6080"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijun Tian","raw_affiliation_strings":["University of Notre Dame, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-2795-6080","affiliations":[{"raw_affiliation_string":"University of Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078270542","display_name":"Maitrey Mehta","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maitrey Mehta","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0009-0009-5358-7486","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0661-7189","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013135203","display_name":"Vivek Srikumar","orcid":"https://orcid.org/0000-0003-0419-6568"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Srikumar","raw_affiliation_strings":["University of Utah, Salt Lake City, Utah, USA"],"raw_orcid":"https://orcid.org/0000-0003-0419-6568","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.95375672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4298","last_page":"4304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9096999764442444,"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":0.9096999764442444,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.035999998450279236,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.012500000186264515,"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/scalability","display_name":"Scalability","score":0.7297999858856201},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.45210000872612},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41130000352859497},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.351500004529953},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.34950000047683716},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.34209999442100525},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.3361999988555908},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.32269999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246999979019165},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7297999858856201},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41130000352859497},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3912000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809869","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809869","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2897754576","https://openalex.org/W2945127593","https://openalex.org/W2951434086","https://openalex.org/W2970641574","https://openalex.org/W3099700870","https://openalex.org/W3154280800","https://openalex.org/W3170739233","https://openalex.org/W3185250692","https://openalex.org/W4284663260","https://openalex.org/W4284664419","https://openalex.org/W4285113563","https://openalex.org/W4385690907","https://openalex.org/W4386576685","https://openalex.org/W4386768656","https://openalex.org/W4396821195","https://openalex.org/W4404780820","https://openalex.org/W4412377148","https://openalex.org/W4412377829","https://openalex.org/W4416034664","https://openalex.org/W7137867298","https://openalex.org/W7138229905"],"related_works":[],"abstract_inverted_index":{"While":[0],"dense":[1,54,116,150],"retrieval":[2,34,155],"models":[3],"have":[4],"been":[5],"the":[6,70,112,118,127,134,165],"standard":[7],"for":[8,26,94,179],"state-of-the-art":[9,123],"information":[10],"retrieval,":[11],"their":[12],"deployment":[13],"is":[14],"often":[15],"constrained":[16],"by":[17,39,169],"high":[18,154],"memory":[19,146],"requirements":[20],"and":[21,75,97,176,190],"reliance":[22],"on":[23,69,126,133,157],"GPU":[24],"accelerators":[25],"vector":[27],"similarity":[28],"search":[29,42,181],"at":[30],"scale.":[31],"Learned":[32],"sparse":[33,66],"offers":[35],"a":[36,62,79,122,162,174],"compelling":[37],"alternative":[38],"enabling":[40],"efficient":[41,177],"via":[43],"inverted":[44],"indices,":[45],"yet":[46],"it":[47],"has":[48],"historically":[49],"received":[50],"less":[51,144],"attention":[52],"than":[53,147],"approaches.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"introduce":[60],"LACONIC,":[61],"family":[63],"of":[64,85,137,164],"learned":[65],"retrievers":[67],"based":[68],"Llama3":[71],"architecture":[72],"(1B,":[73],"3B,":[74],"8B).":[76],"We":[77,183],"propose":[78],"streamlined":[80],"two-phase":[81],"training":[82],"curriculum":[83],"consisting":[84],"(1)":[86],"weakly":[87],"supervised":[88],"pre-finetuning":[89],"to":[90,193],"adapt":[91],"causal":[92],"LLMs":[93],"bidirectional":[95],"contextualization":[96],"(2)":[98],"high-signal":[99],"finetuning":[100],"using":[101],"curated":[102],"hard":[103],"negatives.":[104],"Our":[105],"results":[106],"demonstrate":[107],"that":[108],"LACONIC":[109,172],"effectively":[110],"bridges":[111],"performance":[113],"gap":[114],"with":[115,161],"models:":[117],"8B":[119],"variant":[120],"achieves":[121],"60.2":[124],"nDCG@10":[125],"MTEB":[128],"Retrieval":[129],"benchmark,":[130],"ranking":[131],"15th":[132],"leaderboard":[135],"as":[136],"February":[138],"5th,":[139],"2026,":[140],"while":[141],"utilizing":[142],"74%":[143],"index":[145],"an":[148],"equivalent":[149],"model.":[151],"By":[152],"delivering":[153],"effectiveness":[156],"commodity":[158],"CPU":[159],"hardware":[160],"fraction":[163],"compute":[166],"budget":[167],"required":[168],"competing":[170],"models,":[171],"provides":[173],"scalable":[175],"solution":[178],"real-world":[180],"applications.":[182],"fully":[184],"open":[185],"source":[186],"our":[187],"code":[188],"implementation":[189],"trained":[191],"checkpoints":[192],"facilitate":[194],"reproducibility.":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-11T00:00:00"}