<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-2026-diagnosing">
    <titleInfo>
        <title>Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Edward</namePart>
        <namePart type="given">Y</namePart>
        <namePart type="family">Chang</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</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, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Do frontier LLMs reason causally, or do they pattern-match, yielding under pressure and hedging under uncertainty? We frame causal judgment as evaluation along three axes, Utility, Safety, and Wise Refusal, across Pearl’s Ladder. We introduce Recursive Causal Audit (RCA), a process-integrity evaluator whose Judge has no access to gold labels: it checks whether a model’s answer is entailed by itsown derivation, internally consistent, and not dominated by user hints under pressure. RCA unifies persona and pressure: prompt tone is the intervention that regulates pressure-induced drift. For fine diagnostic resolution we use CAUSALT3, with explicit trap families and standardized pressure protocols. CAUSALT3 reveals a Skepticism Trap (Claude Haiku rejects 60% of valid L1 links) and a Scaling Paradox (GPT-5.2 underperforms GPT-4-Turbo by 55 points on L3, driven by paralysis rather than hallucination). Under RCA, operating points shift toward the high-Utility, high-Safety quadrant without retraining, consistent with much of the observed failure arising from how answers are rendered under pressure rather than from missing causal knowledge.</abstract>
    <identifier type="citekey">chang-2026-diagnosing</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.427/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>8769</start>
            <end>8789</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment
%A Chang, Edward Y.
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F chang-2026-diagnosing
%X Do frontier LLMs reason causally, or do they pattern-match, yielding under pressure and hedging under uncertainty? We frame causal judgment as evaluation along three axes, Utility, Safety, and Wise Refusal, across Pearl’s Ladder. We introduce Recursive Causal Audit (RCA), a process-integrity evaluator whose Judge has no access to gold labels: it checks whether a model’s answer is entailed by itsown derivation, internally consistent, and not dominated by user hints under pressure. RCA unifies persona and pressure: prompt tone is the intervention that regulates pressure-induced drift. For fine diagnostic resolution we use CAUSALT3, with explicit trap families and standardized pressure protocols. CAUSALT3 reveals a Skepticism Trap (Claude Haiku rejects 60% of valid L1 links) and a Scaling Paradox (GPT-5.2 underperforms GPT-4-Turbo by 55 points on L3, driven by paralysis rather than hallucination). Under RCA, operating points shift toward the high-Utility, high-Safety quadrant without retraining, consistent with much of the observed failure arising from how answers are rendered under pressure rather than from missing causal knowledge.
%U https://aclanthology.org/2026.findings-acl.427/
%P 8769-8789

Markdown (Informal)

[Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment](https://aclanthology.org/2026.findings-acl.427/) (Chang, Findings 2026)

• Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment (Chang, Findings 2026)

ACL

• Edward Y Chang. 2026. Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment. In Findings of the Association for Computational Linguistics: ACL 2026, pages 8769–8789, San Diego, California, United States. Association for Computational Linguistics.