{"id":"https://openalex.org/W4410636352","doi":"https://doi.org/10.1145/3701716.3715263","title":"Towards Distributionally Balanced End-to-End Generative Retrieval","display_name":"Towards Distributionally Balanced End-to-End Generative Retrieval","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636352","doi":"https://doi.org/10.1145/3701716.3715263"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715263","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","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/10.1145/3701716.3715263","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053232704","display_name":"Yuxuan Liu","orcid":"https://orcid.org/0009-0002-9684-6416"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxuan Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058154698","display_name":"Tianchi Yang","orcid":"https://orcid.org/0000-0003-1215-8676"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianchi Yang","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065287257","display_name":"Zihan Zhang","orcid":"https://orcid.org/0009-0009-3379-9545"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Zhang","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112539896","display_name":"Minghui Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Song","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014900195","display_name":"Haizhen Huang","orcid":"https://orcid.org/0009-0005-7145-2500"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhen Huang","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016794246","display_name":"Weiwei Deng","orcid":"https://orcid.org/0009-0001-4793-9715"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Deng","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103155713","display_name":"Feng Sun","orcid":"https://orcid.org/0009-0006-0834-0562"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Sun","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022403899","display_name":"Qi Zhang","orcid":"https://orcid.org/0009-0009-7438-7248"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Microsoft AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft AI, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5053232704"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05765163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976000189781189,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9793000221252441,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.732191801071167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6305098533630371},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6044411063194275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3818224370479584}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.732191801071167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6305098533630371},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6044411063194275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3818224370479584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715263","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715263","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636352.pdf","grobid_xml":"https://content.openalex.org/works/W4410636352.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2057978375","https://openalex.org/W2079639858","https://openalex.org/W2131738223","https://openalex.org/W2970927596","https://openalex.org/W2990138404","https://openalex.org/W3099700870","https://openalex.org/W3154670582","https://openalex.org/W3156636935","https://openalex.org/W3168875417","https://openalex.org/W3194782062","https://openalex.org/W3205509771","https://openalex.org/W3215615641","https://openalex.org/W4221166196","https://openalex.org/W4224438163","https://openalex.org/W4252076394","https://openalex.org/W4285254085","https://openalex.org/W4292215729","https://openalex.org/W4312974539","https://openalex.org/W4320465836","https://openalex.org/W4367628274","https://openalex.org/W4385567756","https://openalex.org/W4385571319","https://openalex.org/W4385573970","https://openalex.org/W4387848863","https://openalex.org/W4389519879","https://openalex.org/W6601700763","https://openalex.org/W6810139940","https://openalex.org/W6850138286"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2380075625","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345"],"abstract_inverted_index":{"Generative":[0],"retrieval":[1,31,54,62,94,103,151,189],"represents":[2],"a":[3,36,47,118,127],"promising":[4],"paradigm":[5],"in":[6,24,202],"information":[7,143,148],"retrieval,":[8],"using":[9],"seq2seq":[10],"models":[11],"to":[12,26,39,68,78,122,132,135],"encode":[13],"document":[14,21,42],"features":[15],"as":[16,167],"parameters":[17],"and":[18,53,61,80,102,113,141,173,181,191],"decode":[19],"relevant":[20],"identifiers":[22],"(IDs)":[23],"response":[25],"search":[27],"queries.":[28],"Current":[29],"generative":[30,93],"methods":[32],"typically":[33],"rely":[34],"on":[35,107,179],"pre-processing":[37],"stage":[38],"assign":[40],"static":[41],"IDs,":[43],"which":[44],"can":[45],"introduce":[46],"semantic":[48],"gap":[49],"between":[50],"ID":[51,59,82,100,124,164,192],"assignments":[52,60,101],"objectives.":[55],"However,":[56],"optimizing":[57],"both":[58,188],"end-to-end":[63,92],"is":[64],"challenging,":[65],"particularly":[66],"due":[67],"the":[69,108,133],"long-tailed":[70],"distribution":[71,119],"of":[72,110],"real-world":[73],"data":[74],"that":[75,96,146,185],"often":[76],"leads":[77],"inefficient":[79],"unbalanced":[81],"utilization.":[83],"To":[84],"address":[85],"these":[86],"challenges,":[87],"we":[88],"propose":[89],"ASI++,":[90],"an":[91,142,154],"approach":[95],"jointly":[97],"optimizes":[98],"balanced":[99],"accuracy.":[104],"ASI++":[105,186],"builds":[106],"framework":[109],"vanilla":[111],"ASI":[112],"introduces":[114],"three":[115],"novel":[116],"criteria:":[117],"balancing":[120],"criterion":[121,130,145],"improve":[123],"space":[125],"utilization,":[126],"representation":[128],"bottleneck":[129],"applied":[131],"encoder":[134],"produce":[136],"more":[137],"distinguishable":[138],"dense":[139],"representations,":[140],"consistency":[144],"aligns":[147],"retention":[149],"with":[150,194],"goals":[152],"within":[153],"information-theoretic":[155],"framework.":[156],"We":[157],"also":[158],"examine":[159],"various":[160],"structures":[161],"for":[162],"learning":[163],"assignments,":[165],"such":[166],"neural":[168],"quantization,":[169,172],"differentiable":[170],"product":[171],"residual":[174],"quantization.":[175],"Extensive":[176],"offline":[177],"experiments":[178],"public":[180],"industrial":[182],"datasets":[183],"demonstrate":[184],"improves":[187],"performance":[190],"balance,":[193],"online":[195],"results":[196],"highlighting":[197],"its":[198],"significant":[199],"business":[200],"value":[201],"Microsoft":[203],"Bing":[204],"sponsored":[205],"search.":[206]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}