<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zehle-assenmacher-2026-calibration">
    <titleInfo>
        <title>Can Calibration of Positional Encodings Enhance Long Context Utilization?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tom</namePart>
        <namePart type="family">Zehle</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthias</namePart>
        <namePart type="family">Aßenmacher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Marquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-386-9</identifier>
    </relatedItem>
    <abstract>Large language models suffer from positional biases like the “Lost in the Middle” (LiM) phenomenon and recency bias, which reduce the effective utilization of long contexts. In this work, we investigate the role of Positional Encodings in this context. Our empirical study confirms the persistence of these biases in modern large language models. Drawing on these findings, we introduce Caliope, a training-free framework for calibrating Positional Encodings at inference time. Our calibrators yield substantial improvements on needle-in-a-haystack and cross-chunk reasoning benchmarks, and offer a practical, lightweight method for improving long-context utilization.</abstract>
    <identifier type="citekey">zehle-assenmacher-2026-calibration</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-eacl.120/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>2268</start>
            <end>2280</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Can Calibration of Positional Encodings Enhance Long Context Utilization?
%A Zehle, Tom
%A Aßenmacher, Matthias
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F zehle-assenmacher-2026-calibration
%X Large language models suffer from positional biases like the “Lost in the Middle” (LiM) phenomenon and recency bias, which reduce the effective utilization of long contexts. In this work, we investigate the role of Positional Encodings in this context. Our empirical study confirms the persistence of these biases in modern large language models. Drawing on these findings, we introduce Caliope, a training-free framework for calibrating Positional Encodings at inference time. Our calibrators yield substantial improvements on needle-in-a-haystack and cross-chunk reasoning benchmarks, and offer a practical, lightweight method for improving long-context utilization.
%U https://aclanthology.org/2026.findings-eacl.120/
%P 2268-2280

Markdown (Informal)

[Can Calibration of Positional Encodings Enhance Long Context Utilization?](https://aclanthology.org/2026.findings-eacl.120/) (Zehle & Aßenmacher, Findings 2026)

• Can Calibration of Positional Encodings Enhance Long Context Utilization? (Zehle & Aßenmacher, Findings 2026)

ACL

• Tom Zehle and Matthias Aßenmacher. 2026. Can Calibration of Positional Encodings Enhance Long Context Utilization?. In Findings of the Association for Computational Linguistics: EACL 2026, pages 2268–2280, Rabat, Morocco. Association for Computational Linguistics.