{"id":"https://openalex.org/W7128475469","doi":"https://doi.org/10.48550/arxiv.2602.08457","title":"Hybrid Pooling with LLMs via Relevance Context Learning","display_name":"Hybrid Pooling with LLMs via Relevance Context Learning","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128475469","doi":"https://doi.org/10.48550/arxiv.2602.08457"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.08457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2602.08457","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070408128","display_name":"David Otero","orcid":"https://orcid.org/0000-0003-1139-0449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Otero, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122339156","display_name":"Javier Parapar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parapar, Javier","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":0.8860999941825867,"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":0.8860999941825867,"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":0.029899999499320984,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.008899999782443047,"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/relevance","display_name":"Relevance (law)","score":0.91839998960495},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6254000067710876},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.49300000071525574},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.4000999927520752},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.3395000100135803}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.91839998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621999740600586},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.3395000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.329800009727478},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C2776802673","wikidata":"https://www.wikidata.org/wiki/Q1548396","display_name":"Relevance theory","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2921000123023987}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.08457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2602.08457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"High-quality":[0],"relevance":[1,32,73,103,109,142,148,165,225,230],"judgements":[2,104,240],"over":[3,216],"large":[4],"query":[5],"sets":[6,129],"are":[7,150,200],"essential":[8],"for":[9,117,143,241],"evaluating":[10],"Information":[11],"Retrieval":[12],"(IR)":[13],"systems,":[14],"yet":[15],"manual":[16],"annotation":[17],"remains":[18],"costly":[19],"and":[20,66,134,213],"time-consuming.":[21],"Large":[22],"Language":[23],"Models":[24],"(LLMs)":[25],"have":[26],"recently":[27],"shown":[28],"promise":[29],"as":[30,63,153],"automatic":[31],"assessors,":[33,195],"but":[34],"their":[35],"reliability":[36],"is":[37,191,232],"still":[38],"limited.":[39],"Most":[40],"existing":[41],"approaches":[42],"rely":[43],"on":[44],"zero-shot":[45,211],"prompting":[46,212],"or":[47],"in-context":[48,118],"learning":[49],"(ICL)":[50],"with":[51],"a":[52,76,97,144,158,171,178,184,233],"small":[53],"number":[54],"of":[55,75,130,237],"labelled":[56,115,201],"examples.":[57],"However,":[58],"standard":[59,217],"ICL":[60],"treats":[61],"examples":[62,116,226],"independent":[64],"instances":[65],"fails":[67],"to":[68,81,83,105,127,156],"explicitly":[69,106],"capture":[70],"the":[71,197],"underlying":[72],"criteria":[74],"topic,":[77],"restricting":[78],"its":[79],"ability":[80],"generalise":[82],"unseen":[84],"query-document":[85,132],"pairs.":[86],"To":[87,167],"address":[88],"this":[89],"limitation,":[90],"we":[91,176],"introduce":[92],"Relevance":[93],"Context":[94],"Learning":[95],"(RCL),":[96],"novel":[98],"framework":[99],"that":[100,138,207,223],"leverages":[101],"human":[102,194,239],"model":[107],"topic-specific":[108],"criteria.":[110],"Rather":[111],"than":[112],"directly":[113],"using":[114],"prediction,":[119],"RCL":[120,169,208],"first":[121],"prompts":[122,155],"an":[123],"LLM":[124,160],"(Instructor":[125],"LLM)":[126,162],"analyse":[128],"judged":[131,192],"pairs":[133],"generate":[135],"explicit":[136],"narratives":[137,149,231],"describe":[139],"what":[140],"constitutes":[141],"given":[145],"topic.":[146],"These":[147],"then":[151],"used":[152],"structured":[154],"guide":[157],"second":[159],"(Assessor":[161],"in":[163,170,182],"producing":[164],"judgements.":[166],"evaluate":[168],"realistic":[172],"data":[173],"collection":[174],"setting,":[175],"propose":[177],"hybrid":[179],"pooling":[180],"strategy":[181],"which":[183],"shallow":[185],"depth-k":[186],"pool":[187],"from":[188],"participating":[189],"systems":[190],"by":[193,202],"while":[196],"remaining":[198],"documents":[199],"LLMs.":[203],"Experimental":[204],"results":[205],"demonstrate":[206],"substantially":[209],"outperforms":[210],"consistently":[214],"improves":[215],"ICL.":[218],"Overall,":[219],"our":[220],"findings":[221],"indicate":[222],"transforming":[224],"into":[227],"explicit,":[228],"context-aware":[229],"more":[234],"effective":[235],"way":[236],"exploiting":[238],"LLM-based":[242],"IR":[243],"dataset":[244],"construction.":[245]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-11T00:00:00"}