{"id":"https://openalex.org/W7163985791","doi":"https://doi.org/10.48550/arxiv.2606.09241","title":"Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization","display_name":"Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7163985791","doi":"https://doi.org/10.48550/arxiv.2606.09241"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09241","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.09241","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138214584","display_name":"Yufei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yufei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138286134","display_name":"Zihan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138203931","display_name":"Yubao Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yubao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138207396","display_name":"Yukun Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yukun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138230054","display_name":"Maarten de Rijke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"de Rijke, Maarten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138232336","display_name":"Zhaochun Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Zhaochun","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":0,"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":0.3612000048160553,"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":0.3612000048160553,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.16869999468326569,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.10819999873638153,"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/prefix","display_name":"Prefix","score":0.6726999878883362},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6452000141143799},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5304999947547913},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4350999891757965},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.39590001106262207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39089998602867126},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.3573000133037567},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.3529999852180481},{"id":"https://openalex.org/keywords/huffman-coding","display_name":"Huffman coding","score":0.3398999869823456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701200008392334},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6452000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544700026512146},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.33980000019073486},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29159998893737793},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09241","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.09241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09241","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,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.737001359462738}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"generative":[1,194],"retrieval":[2,5,179,195],"formulates":[3],"multimodal":[4,178,193],"as":[6],"discrete":[7],"identifier":[8,40,188],"generation,":[9],"eliminating":[10],"the":[11,164,172],"need":[12],"for":[13],"explicit":[14],"similarity":[15,162],"search":[16,69,168],"over":[17],"external":[18],"embeddings.":[19],"Existing":[20],"approaches":[21],"construct":[22],"identifiers":[23,61],"via":[24],"residual":[25,140],"quantization":[26,141],"and":[27,45,79,94,150,159,190],"decode":[28],"them":[29],"with":[30,120],"trie-constrained":[31],"beam":[32,68,167],"search.":[33],"This":[34],"combination":[35],"introduces":[36],"an":[37],"indexing-decoding":[38,173],"gap:":[39],"learning":[41],"objectives,":[42],"including":[43],"reconstruction":[44],"contrastive":[46],"losses,":[47],"do":[48],"not":[49],"explicitly":[50],"enforce":[51],"prefix":[52,86,103,113,118,158],"discriminability":[53],"during":[54],"decoding.":[55,95],"As":[56],"a":[57,81,106,127],"result,":[58],"even":[59],"well-optimized":[60],"can":[62],"be":[63],"irreversibly":[64],"pruned":[65],"early":[66,145],"in":[67,92],"due":[70],"to":[71,88,138,143,163],"low-rank":[72],"prefixes.":[73],"We":[74],"theoretically":[75],"characterize":[76],"this":[77,98],"gap":[78],"derive":[80],"survival":[82],"bound":[83],"that":[84,182],"relates":[85],"retention":[87,104,185],"three":[89,110],"controllable":[90],"factors":[91],"indexing":[93],"Building":[96],"on":[97,176],"bound,":[99],"we":[100],"propose":[101],"PRO,":[102],"optimization,":[105],"unified":[107],"framework":[108],"comprising":[109],"mechanisms:":[111],"(i)":[112],"ranking":[114],"distillation":[115],"aligns":[116],"quantized":[117],"rankings":[119],"those":[121],"induced":[122],"by":[123],"pre-quantization":[124],"embeddings":[125],"using":[126],"listwise":[128],"loss;":[129],"(ii)":[130],"vocabulary":[131],"scheduling":[132],"increases":[133],"codebook":[134],"sizes":[135],"from":[136,147],"shallow":[137],"deep":[139],"levels":[142],"reduce":[144],"competition":[146],"non-target":[148],"prefixes;":[149],"(iii)":[151],"geometric":[152],"score":[153],"fusion":[154],"vectorizes":[155],"each":[156],"candidate":[157],"incorporates":[160],"its":[161],"query":[165],"into":[166],"scoring,":[169],"further":[170],"reducing":[171],"mismatch.":[174],"Experiments":[175],"nine":[177],"tasks":[180],"show":[181],"PRO":[183],"improves":[184],"of":[186],"target":[187],"prefixes":[189],"outperforms":[191],"existing":[192],"baselines.":[196]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}