{"id":"https://openalex.org/W7162540881","doi":"https://doi.org/10.48550/arxiv.2605.26578","title":"Is Position Bias in Dense Retrievers Built In-or Learned from Data?","display_name":"Is Position Bias in Dense Retrievers Built In-or Learned from Data?","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162540881","doi":"https://doi.org/10.48550/arxiv.2605.26578"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26578","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.2605.26578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137133245","display_name":"Daegon Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Daegon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109785488","display_name":"SeungYoon Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, SeungYoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137115923","display_name":"Woomyoung Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Woomyoung","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":0.8652999997138977,"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":0.8652999997138977,"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/T10028","display_name":"Topic Modeling","score":0.021400000900030136,"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":0.012799999676644802,"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/ranking","display_name":"Ranking (information retrieval)","score":0.6794999837875366},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.6122000217437744},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5321999788284302},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4390000104904175},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/information-bias","display_name":"Information bias","score":0.3522999882698059}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025000214576721},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479000210762024},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C88629717","wikidata":"https://www.wikidata.org/wiki/Q17056323","display_name":"Information bias","level":3,"score":0.3522999882698059},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26578","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.2605.26578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26578","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"retrievers":[1,31],"exhibit":[2],"positional":[3,27,42,114,139],"bias,":[4],"favoring":[5],"documents":[6],"whose":[7],"query-relevant":[8,64],"information":[9,20],"appears":[10,21,66],"near":[11],"the":[12,19,41,68,89,99,108],"beginning":[13],"and":[14,75,84,165],"degrading":[15],"retrieval":[16,124],"performance":[17,125],"when":[18],"later.":[22],"While":[23],"prior":[24],"work":[25],"on":[26,35,118],"bias":[28,51,164],"in":[29,46,62,126,148,161],"dense":[30],"has":[32],"largely":[33],"focused":[34],"architectural":[36,143],"explanations,":[37],"we":[38,56,92],"study":[39],"how":[40],"distribution":[43,155],"of":[44,73],"evidence":[45,65,106],"training":[47,60,86,103,112],"data":[48,168],"affects":[49],"retrieval-level":[50,162],"direction.":[52],"To":[53],"test":[54],"this,":[55],"construct":[57],"synthetic":[58],"position-targeted":[59],"sets":[61],"which":[63],"at":[67,107],"beginning,":[69],"middle,":[70],"or":[71,144],"end":[72],"documents,":[74],"fine-tune":[76],"eight":[77],"architecturally":[78],"diverse":[79],"pretrained":[80],"models":[81],"under":[82],"position-skewed":[83],"balanced":[85,167],"distributions.":[87],"At":[88],"ranking":[90],"level,":[91],"observe":[93],"a":[94,157,171],"strong":[95],"directional":[96],"pattern":[97],"across":[98],"examined":[100],"models:":[101],"skewed":[102],"distributions":[104],"favor":[105],"corresponding":[109],"positions.":[110],"Position-balanced":[111],"reduces":[113],"sensitivity":[115],"by":[116],"57--87\\%":[117],"position-aware":[119],"benchmarks,":[120],"with":[121],"competitive":[122],"mean":[123],"our":[127],"controlled":[128],"setting.":[129],"Representation-level":[130],"analyses":[131],"further":[132],"suggest":[133,166],"that":[134],"fine-tuning":[135],"often":[136],"reshapes":[137],"learned":[138],"preferences,":[140],"although":[141],"pre-existing":[142],"pretraining-specific":[145],"tendencies":[146],"persist":[147],"some":[149],"models.":[150],"These":[151],"results":[152],"identify":[153],"training-position":[154],"as":[156,170],"major":[158],"controllable":[159],"factor":[160],"position":[163],"curation":[169],"practical":[172],"mitigation":[173],"strategy.":[174]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-28T00:00:00"}