{"id":"https://openalex.org/W7156308116","doi":"https://doi.org/10.48550/arxiv.2604.22180","title":"ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression","display_name":"ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7156308116","doi":"https://doi.org/10.48550/arxiv.2604.22180"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.22180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22180","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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.2604.22180","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134708110","display_name":"Xiaojie Ke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke, Xiaojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134693460","display_name":"Shuai Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044919704","display_name":"Li Sun","orcid":"https://orcid.org/0000-0002-4991-655X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Liansheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134718140","display_name":"Yongjin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yongjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134719940","display_name":"Hengjun Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Hengjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134741856","display_name":"Xiangkun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiangkun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134712551","display_name":"Cunxin Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Cunxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134676327","display_name":"Jian Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134686332","display_name":"Guanjun Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Guanjun","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":0.6819999814033508,"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":0.6819999814033508,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03519999980926514,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.03020000085234642,"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/residual","display_name":"Residual","score":0.5583000183105469},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.534600019454956},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5145000219345093},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5126000046730042},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5101000070571899},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4341000020503998},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3828999996185303},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8355000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570900022983551},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2779338814","wikidata":"https://www.wikidata.org/wiki/Q5179285","display_name":"Covert","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.22180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22180","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.22180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22180","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"based":[4],"listwise":[5,116],"reranking":[6,193],"has":[7],"emerged":[8],"as":[9,45],"the":[10,30,36,39,50,109,120,123,128,146,151,162,182],"dominant":[11],"paradigm":[12],"for":[13,61,115],"achieving":[14,186],"state-of-the-art":[15],"ranking":[16,43,129,217],"effectiveness":[17,218,241],"in":[18,38],"information":[19],"retrieval.":[20],"However,":[21],"its":[22],"reliance":[23],"on":[24,201],"feeding":[25],"full":[26],"passage":[27,99],"texts":[28],"into":[29,87,100,112],"LLM":[31],"introduces":[32],"two":[33],"critical":[34],"bottlenecks:":[35],"\"lost":[37],"middle\"":[40],"phenomenon":[41],"degrades":[42],"quality":[44],"input":[46],"length":[47],"grows,":[48],"and":[49,127,184,192,205,228,242],"inference":[51],"latency":[52],"scales":[53],"super-linearly":[54],"with":[55,141,155],"sequence":[56],"length,":[57],"rendering":[58],"it":[59],"impractical":[60],"industrial":[62],"deployment.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,131,149],"present":[68],"ResRank,":[69],"a":[70,101,113,133,156,170,236],"unified":[71],"retrieval-reranking":[72],"framework":[73],"that":[74,83,137,179,211],"fundamentally":[75,237],"addresses":[76],"both":[77],"challenges.":[78],"Inspired":[79],"by":[80],"multimodal":[81],"LLMs":[82],"project":[84],"visual":[85],"inputs":[86],"compact":[88],"token":[89,232],"representations,":[90],"ResRank":[91,166,212],"employs":[92],"an":[93],"Encoder-LLM":[94],"to":[95,220],"compress":[96],"each":[97],"candidate":[98],"single":[102],"embedding,":[103],"which":[104],"is":[105,167],"then":[106],"fed":[107],"alongside":[108],"query":[110],"text":[111],"Reranker-LLM":[114],"ranking.":[117],"To":[118],"alleviate":[119],"misalignment":[121],"between":[122,190,240],"compressed":[124],"representation":[125],"space":[126],"space,":[130],"introduce":[132],"residual":[134],"connection":[135],"structure":[136],"combines":[138],"encoder":[139,183],"embeddings":[140],"contextualized":[142],"hidden":[143],"states":[144],"from":[145],"reranker.":[147],"Furthermore,":[148],"replace":[150],"conventional":[152],"autoregressive":[153],"decoding":[154],"one-step":[157],"cosine-similarity-based":[158],"scoring":[159],"mechanism,":[160],"eliminating":[161],"generation":[163],"bottleneck":[164],"entirely.":[165],"trained":[168],"through":[169],"carefully":[171],"designed":[172],"dual-stage,":[173],"multi-task,":[174],"end-to-end":[175],"joint":[176],"optimization":[177],"strategy":[178],"simultaneously":[180],"trains":[181],"reranker,":[185],"learning":[187],"objective":[188],"alignment":[189],"retrieval":[191],"while":[194,223],"substantially":[195],"reducing":[196],"training":[197],"complexity.":[198],"Extensive":[199],"experiments":[200],"TREC":[202],"Deep":[203],"Learning":[204],"eight":[206],"BEIR":[207],"benchmark":[208],"datasets":[209],"demonstrate":[210],"achieves":[213],"competitive":[214],"or":[215],"superior":[216],"compared":[219],"existing":[221],"approaches":[222],"requiring":[224],"zero":[225],"generated":[226],"tokens":[227],"processing":[229],"only":[230],"one":[231],"per":[233],"passage,":[234],"yielding":[235],"better":[238],"balance":[239],"efficiency.":[243]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-28T00:00:00"}