<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="son-etal-2026-trontor">
    <titleInfo>
        <title>TRONTOR: To RoPE or Not to RoPE for Long-Context Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Youngjun</namePart>
        <namePart type="family">Son</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jongyeon</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaejin</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>While Rotary Position Embedding (RoPE) is widely used in large language models, its inductive biases can impair long-context reasoning and lead to attention sinks. In this work, we propose TRONTOR, a method that effectively combines RoPE and No Positional Encoding (NoPE) through a simple fine-tuning phase, bypassing the need for expensive pretraining modifications. Our preliminary experiments demonstrate that mixing RoPE and NoPE at the attention-head level can enhance long-context capabilities, while static selection strategies fail to capture the varying complexity of inputs. Based on this observation, TRONTOR employs a lightweight context-aware routing method that dynamically switches each attention head between RoPE and NoPE at every token step. This router-only configuration provides an efficient operating point, yielding long-context performance gains with minimal inference overhead. For further gains, we extend TRONTOR to TRONTOR-Agg, which applies simple unweighted averaging over multiple RoPE bases within RoPE-active heads while avoiding learnable intra-head routing. Evaluated on the RULER benchmark using Llama-3.2 (1B and 3B) and Qwen3 (1.7B and 4B), TRONTOR improves long-context performance by mitigating attention sinks and dynamically reallocating attention toward relevant mid-context tokens.</abstract>
    <identifier type="citekey">son-etal-2026-trontor</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.836/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>17720</start>
            <end>17733</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TRONTOR: To RoPE or Not to RoPE for Long-Context Modeling
%A Son, Youngjun
%A Park, Jongyeon
%A Lee, Jaejin
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F son-etal-2026-trontor
%X While Rotary Position Embedding (RoPE) is widely used in large language models, its inductive biases can impair long-context reasoning and lead to attention sinks. In this work, we propose TRONTOR, a method that effectively combines RoPE and No Positional Encoding (NoPE) through a simple fine-tuning phase, bypassing the need for expensive pretraining modifications. Our preliminary experiments demonstrate that mixing RoPE and NoPE at the attention-head level can enhance long-context capabilities, while static selection strategies fail to capture the varying complexity of inputs. Based on this observation, TRONTOR employs a lightweight context-aware routing method that dynamically switches each attention head between RoPE and NoPE at every token step. This router-only configuration provides an efficient operating point, yielding long-context performance gains with minimal inference overhead. For further gains, we extend TRONTOR to TRONTOR-Agg, which applies simple unweighted averaging over multiple RoPE bases within RoPE-active heads while avoiding learnable intra-head routing. Evaluated on the RULER benchmark using Llama-3.2 (1B and 3B) and Qwen3 (1.7B and 4B), TRONTOR improves long-context performance by mitigating attention sinks and dynamically reallocating attention toward relevant mid-context tokens.
%U https://aclanthology.org/2026.findings-emnlp.836/
%P 17720-17733

Markdown (Informal)

[TRONTOR: To RoPE or Not to RoPE for Long-Context Modeling](https://aclanthology.org/2026.findings-emnlp.836/) (Son et al., Findings 2026)

• TRONTOR: To RoPE or Not to RoPE for Long-Context Modeling (Son et al., Findings 2026)

ACL

• Youngjun Son, Jongyeon Park, and Jaejin Lee. 2026. TRONTOR: To RoPE or Not to RoPE for Long-Context Modeling. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 17720–17733, Budapest, Hungary. Association for Computational Linguistics.