<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kayan-zhang-2026-prototype">
    <titleInfo>
        <title>Prototype-Based Dynamic Steering for Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ceyhun</namePart>
        <namePart type="given">Efe</namePart>
        <namePart type="family">Kayan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Li</namePart>
        <namePart type="family">Zhang</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning amplification. We present Prototype-Based Dynamic Steering (PDS), a test-time method that amplifies large language model (LLM) reasoning without adding or altering instructions. We introduce “reasoning prototypes” by clustering activation differences between Chain-of-Thought (CoT) and neutral prompts. At inference, an input’s hidden state is projected onto these prototypes to form an instance-specific steering vector. Evaluated on GSM8K, AQuA-RAT, and BIG-Bench tasks, PDS consistently improves accuracy without fine-tuning or prompt engineering. Notably, the gains persist even when CoT is explicitly suppressed to improve cost-efficiency, indicating that the intervention strengthens latent reasoning processes rather than inducing a superficial behavioral shift. These results position dynamic, prototype-guided steering as a lightweight alternative to training-time approaches for enhancing LLM reasoning.</abstract>
    <identifier type="citekey">kayan-zhang-2026-prototype</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2442/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>55412</start>
            <end>55425</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prototype-Based Dynamic Steering for Large Language Models
%A Kayan, Ceyhun Efe
%A Zhang, Li
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F kayan-zhang-2026-prototype
%X Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning amplification. We present Prototype-Based Dynamic Steering (PDS), a test-time method that amplifies large language model (LLM) reasoning without adding or altering instructions. We introduce “reasoning prototypes” by clustering activation differences between Chain-of-Thought (CoT) and neutral prompts. At inference, an input’s hidden state is projected onto these prototypes to form an instance-specific steering vector. Evaluated on GSM8K, AQuA-RAT, and BIG-Bench tasks, PDS consistently improves accuracy without fine-tuning or prompt engineering. Notably, the gains persist even when CoT is explicitly suppressed to improve cost-efficiency, indicating that the intervention strengthens latent reasoning processes rather than inducing a superficial behavioral shift. These results position dynamic, prototype-guided steering as a lightweight alternative to training-time approaches for enhancing LLM reasoning.
%U https://aclanthology.org/2026.emnlp-main.2442/
%P 55412-55425

Markdown (Informal)

[Prototype-Based Dynamic Steering for Large Language Models](https://aclanthology.org/2026.emnlp-main.2442/) (Kayan & Zhang, EMNLP 2026)

• Prototype-Based Dynamic Steering for Large Language Models (Kayan & Zhang, EMNLP 2026)

ACL

• Ceyhun Efe Kayan and Li Zhang. 2026. Prototype-Based Dynamic Steering for Large Language Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 55412–55425, Budapest, Hungary. Association for Computational Linguistics.