{"id":"https://openalex.org/W7165129584","doi":"https://doi.org/10.48550/arxiv.2606.18781","title":"Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation","display_name":"Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation","publication_year":2026,"publication_date":"2026-06-17","ids":{"openalex":"https://openalex.org/W7165129584","doi":"https://doi.org/10.48550/arxiv.2606.18781"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.18781","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18781","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":"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.2606.18781","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138945677","display_name":"Shanshan Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Shanshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138847919","display_name":"Yiwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138924378","display_name":"Yujun Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Yujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138858623","display_name":"Jiafeng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Jiafeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103870133","display_name":"Liu S","orcid":"https://orcid.org/0000-0001-7255-0982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shenghua","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":0.784500002861023,"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":0.784500002861023,"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/T11269","display_name":"Algorithms and Data Compression","score":0.04809999838471413,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.024900000542402267,"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/dice","display_name":"Dice","score":0.9341999888420105},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6632000207901001},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5112000107765198},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4262999892234802},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.3564000129699707},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.32919999957084656}],"concepts":[{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.9341999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156999707221985},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6632000207901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385000109672546},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48500001430511475},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4788999855518341},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.18781","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18781","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":"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.2606.18781","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18781","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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"retrieval":[1,110],"ranks":[2],"one":[3,7],"query":[4],"vector":[5,99],"against":[6],"document":[8,26],"vector.":[9],"On":[10,106],"long":[11],"documents,":[12],"this":[13,32,66],"interface":[14],"can":[15],"fail":[16],"when":[17],"a":[18,50,76,89,97,161],"short":[19],"but":[20],"decisive":[21],"span":[22],"is":[23],"weakened":[24],"during":[25],"encoding":[27,159],"before":[28],"ranking.":[29],"We":[30],"study":[31],"failure":[33],"mode":[34],"as":[35,160],"document-side":[36,78],"early":[37],"compression":[38],"and":[39,92,132,163],"introduce":[40],"the":[41,55,60,102,115,148],"Evidence":[42],"Dilution":[43],"Index":[44],"(EDI)":[45],"to":[46,130,137],"measure":[47],"how":[48],"far":[49],"document-level":[51,158],"representation":[52],"falls":[53],"below":[54],"strongest":[56],"chunk-level":[57],"evidence":[58],"within":[59],"same":[61],"gold":[62],"document.":[63],"Guided":[64],"by":[65],"view,":[67],"we":[68],"propose":[69],"DICE":[70,108,143],"(Document":[71],"Inference":[72],"via":[73],"Chunk":[74],"Evidence),":[75],"training-free":[77],"strategy":[79],"that":[80],"splits":[81],"documents":[82],"into":[83,96],"chunks,":[84],"encodes":[85],"them":[86,94],"independently":[87],"with":[88,114],"frozen":[90],"model,":[91],"aggregates":[93],"back":[95],"single":[98],"while":[100],"preserving":[101],"standard":[103],"one-query-one-document":[104],"interface.":[105],"LongEmbed,":[107],"improves":[109],"across":[111],"four":[112],"backbones,":[113],"largest":[116],"gains":[117],"on":[118],"slices":[119],"beyond":[120],"4k":[121],"tokens:":[122],"for":[123,166],"Dream,":[124],"Passkey":[125],">4k":[126,134],"rises":[127],"from":[128,135],"30.0":[129],"90.0":[131],"Needle":[133],"23.3":[136],"74.0.":[138],"Across":[139],"12,779":[140],"filtered":[141],"samples,":[142],"yields":[144],"lower":[145],"EDI":[146],"than":[147],"single-vector":[149],"baseline":[150],"in":[151],"92.8%":[152],"of":[153],"cases.":[154],"These":[155],"results":[156],"establish":[157],"practical":[162],"underexplored":[164],"lever":[165],"long-document":[167],"retrieval.":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-19T00:00:00"}