<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dinh-2026-one">
    <titleInfo>
        <title>One and Only at SemEval-2026 Task 2: Evaluating Zero-Shot Autonomous LLM Agents and Heuristic Proxies in Ecological Affect Forecasting</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nam</namePart>
        <namePart type="family">Dinh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Kochmar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mamoru</namePart>
            <namePart type="family">Komachi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-414-9</identifier>
    </relatedItem>
    <abstract>This paper presents team One and Only’s sys-tem for SemEval-2026 Task 2: PredictingVariation in Emotional Valence and Arousalover Time (Soni et al., 2026). We investigatewhether zero-shot LLM reasoning can replacefine-tuning for ecological affect forecasting bycombining deterministic statistical priors withfrozen LLMs (Gemini 3 Pro, Claude Opus4.6, GPT-5.2). For short-term state changes(Subtask 2A), an OLS mean-reversion anchoris paired with LLM-generated impulses; forlong-term disposition changes (Subtask 2B),a Chain-of-Thought prompt drives direct nu-meric prediction. Our system underperformsfine-tuned approaches on both subtasks. How-ever, post-submission ablation across threeLLMs reveals a task-dependent pattern: CoTreasoning substantially improves dispositionforecasting (rV : \ensuremath-0.185 → +0.129; MAEV :0.899 → 0.422), while uncalibrated LLM im-pulses degrade state-change prediction due tovariance collapse (\ensuremathσpred = 0.41 vs. \ensuremathσgold =1.73). We provide a detailed diagnostic anal-ysis of these failure modes and release allprompts and outputs for reproducibility.</abstract>
    <identifier type="citekey">dinh-2026-one</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.162/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1205</start>
            <end>1211</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T One and Only at SemEval-2026 Task 2: Evaluating Zero-Shot Autonomous LLM Agents and Heuristic Proxies in Ecological Affect Forecasting
%A Dinh, Nam
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F dinh-2026-one
%X This paper presents team One and Only’s sys-tem for SemEval-2026 Task 2: PredictingVariation in Emotional Valence and Arousalover Time (Soni et al., 2026). We investigatewhether zero-shot LLM reasoning can replacefine-tuning for ecological affect forecasting bycombining deterministic statistical priors withfrozen LLMs (Gemini 3 Pro, Claude Opus4.6, GPT-5.2). For short-term state changes(Subtask 2A), an OLS mean-reversion anchoris paired with LLM-generated impulses; forlong-term disposition changes (Subtask 2B),a Chain-of-Thought prompt drives direct nu-meric prediction. Our system underperformsfine-tuned approaches on both subtasks. How-ever, post-submission ablation across threeLLMs reveals a task-dependent pattern: CoTreasoning substantially improves dispositionforecasting (rV : \ensuremath-0.185 → +0.129; MAEV :0.899 → 0.422), while uncalibrated LLM im-pulses degrade state-change prediction due tovariance collapse (\ensuremathσpred = 0.41 vs. \ensuremathσgold =1.73). We provide a detailed diagnostic anal-ysis of these failure modes and release allprompts and outputs for reproducibility.
%U https://aclanthology.org/2026.semeval-1.162/
%P 1205-1211

Markdown (Informal)

[One and Only at SemEval-2026 Task 2: Evaluating Zero-Shot Autonomous LLM Agents and Heuristic Proxies in Ecological Affect Forecasting](https://aclanthology.org/2026.semeval-1.162/) (Dinh, SemEval 2026)

• One and Only at SemEval-2026 Task 2: Evaluating Zero-Shot Autonomous LLM Agents and Heuristic Proxies in Ecological Affect Forecasting (Dinh, SemEval 2026)

ACL

• Nam Dinh. 2026. One and Only at SemEval-2026 Task 2: Evaluating Zero-Shot Autonomous LLM Agents and Heuristic Proxies in Ecological Affect Forecasting. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1205–1211, San Diego, California, USA. Association for Computational Linguistics.