{"id":"https://openalex.org/W7164404318","doi":"https://doi.org/10.48550/arxiv.2606.11700","title":"CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring","display_name":"CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164404318","doi":"https://doi.org/10.48550/arxiv.2606.11700"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11700","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11700","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.2606.11700","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138478614","display_name":"Xuan Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134761192","display_name":"Haohang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Haohang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138444615","display_name":"Yingqi Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Yingqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138457371","display_name":"Junlong Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Junlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138408851","display_name":"Yuxuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138468894","display_name":"Ping Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Ping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138468772","display_name":"Rui Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138448743","display_name":"Xiaoyu Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Xiaoyu","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/T10028","display_name":"Topic Modeling","score":0.35679998993873596,"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":0.35679998993873596,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.16740000247955322,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.05299999937415123,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8701000213623047},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6481999754905701},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5917999744415283},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5315999984741211},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5256999731063843},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41769999265670776},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.35530000925064087}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8701000213623047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363999724388123},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.454800009727478},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41760000586509705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33889999985694885},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11700","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11700","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.2606.11700","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11700","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],"rerankers":[4],"have":[5],"become":[6],"an":[7,110,175],"important":[8],"component":[9],"of":[10,50,106,113,136],"modern":[11],"retrieval":[12],"and":[13,60,76,155,170],"retrieval-augmented":[14],"generation":[15],"pipelines,":[16],"but":[17],"their":[18,23],"high":[19],"computational":[20],"cost":[21],"limits":[22],"applicability":[24],"to":[25,71,138],"long":[26],"candidate":[27,58,134],"lists.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"propose":[33],"\\textbf{CompRank},":[34],"a":[35,78],"token-efficient":[36],"reranking":[37,100,154],"framework":[38],"that":[39,81,96,127,167],"reduces":[40],"redundant":[41],"computation":[42],"by":[43],"aligning":[44],"reranker":[45],"design":[46],"with":[47,87,116],"the":[48,160],"sparsity":[49],"ranking":[51],"signals.":[52],"CompRank":[53,97,128,162],"decouples":[54],"document":[55,85,107],"representations":[56],"from":[57],"order":[59],"query":[61],"context,":[62],"enabling":[63],"reusable":[64],"document-side":[65],"states;":[66],"applies":[67],"segment-wise":[68],"token":[69],"compression":[70,169],"reduce":[72],"query--document":[73],"interaction":[74],"cost;":[75],"introduces":[77],"CopyNet-style":[79],"objective":[80],"directly":[82],"aligns":[83],"attention-based":[84],"scoring":[86,173],"training":[88,142],"supervision.":[89],"Experiments":[90],"on":[91,124,133,143],"seven":[92],"BEIR":[93],"datasets":[94],"show":[95,126],"achieves":[98],"strong":[99],"performance":[101],"while":[102,146],"retaining":[103],"only":[104],"10.2\\%":[105],"tokens,":[108],"reaching":[109],"average":[111],"NDCG@10":[112],"39.2":[114],"compared":[115],"39.7":[117],"under":[118],"full-token":[119,161],"attention.":[120],"Further":[121],"scaling":[122],"experiments":[123],"TREC-COVID":[125],"remains":[129],"stable":[130],"when":[131],"evaluated":[132],"lists":[135],"up":[137],"500":[139],"documents":[140],"after":[141],"30-document":[144],"lists,":[145],"achieving":[147],"$4.9\\times$--$9.5\\times$":[148],"end-to-end":[149],"speedup":[150,158],"over":[151,159],"generation-based":[152],"listwise":[153],"approximately":[156],"$1.3\\times$":[157],"variant.":[163],"These":[164],"results":[165],"suggest":[166],"token-level":[168],"decoding-free":[171],"attention":[172],"provide":[174],"effective":[176],"path":[177],"toward":[178],"scalable":[179],"LLM-based":[180],"reranking.":[181]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}