{"id":"https://openalex.org/W7140110649","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.120","title":"Can Calibration of Positional Encodings Enhance Long Context Utilization?","display_name":"Can Calibration of Positional Encodings Enhance Long Context Utilization?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140110649","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.120"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.120","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.120","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.120","pdf_url":"https://aclanthology.org/2026.findings-eacl.120.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.120.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119949048","display_name":"Tom Zehle","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Zehle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069469652","display_name":"Matthias A\u00dfenmacher","orcid":"https://orcid.org/0000-0003-2154-5774","observed_orcids":["https://orcid.org/0000-0003-2154-5774"]},"institutions":[{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":"DE","type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias A\u00dfenmacher","raw_affiliation_strings":["LMU Munich , Germany,","Munich Center for Machine Learning (MCML) , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich , Germany,","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Munich Center for Machine Learning (MCML) , Germany","institution_ids":["https://openalex.org/I4403386549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14624595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2268","last_page":"2280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9653000235557556,"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":0.9653000235557556,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.023499999195337296,"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":0.005200000014156103,"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/positional-encoding","display_name":"positional encoding","score":0.8949999809265137},{"id":"https://openalex.org/keywords/position-bias","display_name":"position bias","score":0.7450000047683716},{"id":"https://openalex.org/keywords/recency-bias","display_name":"recency bias","score":0.9940000176429749},{"id":"https://openalex.org/keywords/needle-in-a-haystack","display_name":"needle in a haystack","score":0.7409999966621399},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8999999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147000193595886},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149000287055969},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.24969999492168427},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24580000340938568},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.23970000445842743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23849999904632568}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.120","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.120","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.120","pdf_url":"https://aclanthology.org/2026.findings-eacl.120.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.120","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.120","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.120","pdf_url":"https://aclanthology.org/2026.findings-eacl.120.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2208847381","display_name":"BERD@NFDI  NFDI f\u00fcr Wirtschaftsdaten und Verwandtes","funder_award_id":"460037581","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7699649992","display_name":"European Large Open Multi-Modal Foundation Models For Robust Generalization On Arbitrary Data Streams","funder_award_id":"101214398","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140110649.pdf","grobid_xml":"https://content.openalex.org/works/W7140110649.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412888637","https://openalex.org/W4402684028","https://openalex.org/W7166799184","https://openalex.org/W7166847147","https://openalex.org/W4415797266","https://openalex.org/W4412886650","https://openalex.org/W4415194346","https://openalex.org/W6947890523","https://openalex.org/W4399424779","https://openalex.org/W4393924636"],"abstract_inverted_index":{"Large":[0],"language":[1,49],"models":[2],"suffer":[3],"from":[4],"positional":[5,33,62],"biases":[6,45],"like":[7],"the":[8,11,20,30,41],"\"Lost":[9],"in":[10,35,46],"Middle\"":[12],"(LiM)":[13],"phenomenon":[14],"and":[15,73,77],"recency":[16],"bias,":[17],"which":[18],"reduce":[19],"effective":[21],"utilization":[22],"of":[23,32,43],"long":[24],"contexts.In":[25],"this":[26,36],"work,":[27],"we":[28,54],"investigate":[29],"role":[31],"encodings":[34,63],"context.Our":[37],"empirical":[38],"study":[39],"confirms":[40],"persistence":[42],"these":[44,52],"modern":[47],"large":[48],"models.Drawing":[50],"on":[51,71],"findings,":[53],"introduce":[55],"CALIOPE,":[56],"a":[57,79],"training-free":[58],"framework":[59],"for":[60,83],"calibrating":[61],"at":[64],"inference":[65],"time.Our":[66],"calibrators":[67],"yield":[68],"substantial":[69],"improvements":[70],"needle-in-a-haystack":[72],"cross-chunk":[74],"reasoning":[75],"benchmarks,":[76],"offer":[78],"practical,":[80],"lightweight":[81],"method":[82],"improving":[84],"long-context":[85],"utilization.":[86]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}