<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tikhonov-etal-2026-confidence">
    <titleInfo>
        <title>Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pavel</namePart>
        <namePart type="family">Tikhonov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Oseledets</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elena</namePart>
        <namePart type="family">Tutubalina</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>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</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">979-8-89176-381-4</identifier>
    </relatedItem>
    <abstract>We challenge the common assumption that Large Language Models (LLMs) build confidence gradually during reasoning. Instead, we find that conviction is often reached in a discrete “moment of insight”, characterized by a sudden and sharp increase in an answer’s probability-a phenomenon we term a “confidence leap”. Leveraging this discovery, we introduce a training-free, model-agnostic early-stopping heuristic that halts generation upon detecting such a leap, significantly reducing the generation length without sacrificing accuracy. We also demonstrate that the reasoning text leading up to this leap is semantically potent and transferable: feeding this partial reasoning to a different model family substantially boosts its performance. This suggests that the “confidence leap” marks a shared, interpretable reasoning milestone, not just a model-specific statistical artifact.</abstract>
    <identifier type="citekey">tikhonov-etal-2026-confidence</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-short.43/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>602</start>
            <end>616</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer
%A Tikhonov, Pavel
%A Oseledets, Ivan
%A Tutubalina, Elena
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-381-4
%F tikhonov-etal-2026-confidence
%X We challenge the common assumption that Large Language Models (LLMs) build confidence gradually during reasoning. Instead, we find that conviction is often reached in a discrete “moment of insight”, characterized by a sudden and sharp increase in an answer’s probability-a phenomenon we term a “confidence leap”. Leveraging this discovery, we introduce a training-free, model-agnostic early-stopping heuristic that halts generation upon detecting such a leap, significantly reducing the generation length without sacrificing accuracy. We also demonstrate that the reasoning text leading up to this leap is semantically potent and transferable: feeding this partial reasoning to a different model family substantially boosts its performance. This suggests that the “confidence leap” marks a shared, interpretable reasoning milestone, not just a model-specific statistical artifact.
%U https://aclanthology.org/2026.eacl-short.43/
%P 602-616

Markdown (Informal)

[Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer](https://aclanthology.org/2026.eacl-short.43/) (Tikhonov et al., EACL 2026)

• Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer (Tikhonov et al., EACL 2026)

ACL

• Pavel Tikhonov, Ivan Oseledets, and Elena Tutubalina. 2026. Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 602–616, Rabat, Morocco. Association for Computational Linguistics.