<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-2026-yfpo">
    <titleInfo>
        <title>YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yifan</namePart>
        <namePart type="family">Le</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-444-6</identifier>
    </relatedItem>
    <abstract>Preference optimization has become a widely used post-training paradigm for improving the reasoning abilities of large language models. Existing methods typically learn from preferred and dispreferred responses as external behavioral supervision, while largely ignoring capability-related signals encoded in the model’s internal representations. In this work, we study whether such internal signals can provide useful auxiliary supervision for mathematical reasoning. We introduce YFPO (Yoked Feature Preference Optimization), a neuron-guided preference optimization framework that couples response-level preference learning with neuron-level rewards. YFPO first uses AttnLRP to identify math-associated internal features, and then derives an auxiliary reward from the activation margin of these neurons between preferred and dispreferred responses. This reward is combined with the standard preference optimization objective, encouraging the model to align external preferences with internal math-related features. We conduct small-scale experiments on GSM8K with a compact language model. Results show that neuron-guided rewards can influence preference optimization dynamics and yield measurable improvements in several settings, suggesting that internal representations can serve as lightweight and interpretable signals for reasoning-oriented post-training.</abstract>
    <identifier type="citekey">le-2026-yfpo</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-aacl.116/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>2291</start>
            <end>2298</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards
%A Le, Yifan
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F le-2026-yfpo
%X Preference optimization has become a widely used post-training paradigm for improving the reasoning abilities of large language models. Existing methods typically learn from preferred and dispreferred responses as external behavioral supervision, while largely ignoring capability-related signals encoded in the model’s internal representations. In this work, we study whether such internal signals can provide useful auxiliary supervision for mathematical reasoning. We introduce YFPO (Yoked Feature Preference Optimization), a neuron-guided preference optimization framework that couples response-level preference learning with neuron-level rewards. YFPO first uses AttnLRP to identify math-associated internal features, and then derives an auxiliary reward from the activation margin of these neurons between preferred and dispreferred responses. This reward is combined with the standard preference optimization objective, encouraging the model to align external preferences with internal math-related features. We conduct small-scale experiments on GSM8K with a compact language model. Results show that neuron-guided rewards can influence preference optimization dynamics and yield measurable improvements in several settings, suggesting that internal representations can serve as lightweight and interpretable signals for reasoning-oriented post-training.
%U https://aclanthology.org/2026.findings-aacl.116/
%P 2291-2298

Markdown (Informal)

[YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards](https://aclanthology.org/2026.findings-aacl.116/) (Le, Findings 2026)

• YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards (Le, Findings 2026)

ACL

• Yifan Le. 2026. YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 2291–2298, Hengqin, China. Association for Computational Linguistics.