{"id":"https://openalex.org/W7163347971","doi":"https://doi.org/10.48550/arxiv.2606.02814","title":"Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors","display_name":"Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163347971","doi":"https://doi.org/10.48550/arxiv.2606.02814"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.02814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02814","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.2606.02814","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026489372","display_name":"Francisco Valentini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valentini, Francisco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137715034","display_name":"Edgar Altszyler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Altszyler, Edgar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137761704","display_name":"Martin Fajcik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fajcik, Martin","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":0.43140000104904175,"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":0.43140000104904175,"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":0.16130000352859497,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.03869999945163727,"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/relevance","display_name":"Relevance (law)","score":0.8137999773025513},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.801800012588501},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6712999939918518},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5892000198364258},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.520799994468689},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5167999863624573},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4909000098705292},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4422000050544739}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8137999773025513},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.801800012588501},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6712999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6353999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6211000084877014},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5892000198364258},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4909000098705292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4652000069618225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4643999934196472},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.02814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02814","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.2606.02814","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02814","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5042027235031128,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"retrievers":[1,44,84,94,133],"are":[2,104,118],"trained":[3,208],"to":[4,100,121,158],"estimate":[5,69],"query-document":[6,10],"relevance":[7,49,96],"from":[8],"annotated":[9,66,210],"pairs.":[11],"Yet":[12],"annotation":[13],"protocols":[14],"may":[15],"not":[16,213],"purely":[17],"reflect":[18],"relevance:":[19],"they":[20],"select":[21],"only":[22],"a":[23,47,51,60,111,201],"subset":[24],"of":[25,63,163,194,204],"documents":[26,102,114,156,182,189],"for":[27],"labeling,":[28],"and":[29,80,103,137,142],"this":[30,70,179],"selection":[31],"can":[32],"favor":[33],"certain":[34],"document":[35,78,221],"types":[36],"over":[37],"others.":[38],"We":[39,68,89],"investigate":[40],"whether":[41],"supervised":[42,92,131,205],"bi-encoder":[43],"implicitly":[45],"learn":[46,215],"document-level":[48],"prior:":[50],"query-independent":[52],"signal":[53],"encoded":[54],"in":[55,130,140,223],"their":[56,195,224],"representation":[57],"space":[58],"as":[59],"side":[61],"effect":[62,128],"training":[64,73,225],"on":[65,76,209],"data.":[67,226],"prior":[71,117],"by":[72],"simple":[74],"classifiers":[75],"frozen":[77],"embeddings":[79],"evaluate":[81],"three":[82],"state-of-the-art":[83],"across":[85,106],"multiple":[86],"IR":[87],"benchmarks.":[88],"find":[90,153],"that":[91,98,154,190],"neural":[93],"encode":[95],"priors":[97,109],"generalize":[99],"unseen":[101],"consistent":[105,139],"models.":[107],"These":[108],"create":[110],"findability":[112],"gap:":[113],"with":[115,183],"lower":[116],"systematically":[119],"harder":[120],"retrieve,":[122],"even":[123],"when":[124],"genuinely":[125],"relevant.":[126],"This":[127],"appears":[129],"dense":[132],"but":[134,217],"is":[135,173],"weaker":[136],"less":[138],"BM25,":[141],"it":[143],"persists":[144],"under":[145],"controlled":[146],"matched-document":[147],"comparisons.":[148],"Using":[149],"LLM-based":[150],"explanations,":[151],"we":[152],"judged-relevant":[155],"tend":[157],"be":[159],"comprehensive,":[160],"self-contained":[161],"summaries":[162],"mainstream":[164],"topics,":[165],"while":[166],"niche,":[167],"fragmentary,":[168],"or":[169],"highly":[170],"technical":[171],"content":[172],"often":[174],"left":[175],"unjudged.":[176],"Retrievers":[177],"internalize":[178],"bias,":[180],"ranking":[181],"these":[184],"favored":[185],"features":[186],"higher":[187],"than":[188],"lack":[191],"them,":[192],"independently":[193],"actual":[196],"relevance.":[197],"Our":[198],"findings":[199],"expose":[200],"structural":[202],"limitation":[203],"retrieval:":[206],"models":[207],"data":[211],"do":[212],"just":[214],"relevance,":[216],"also":[218],"the":[219],"implicit":[220],"preferences":[222]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}