<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2026-critical">
    <titleInfo>
        <title>Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Eunkyu</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wesley</namePart>
        <namePart type="given">Hanwen</namePart>
        <namePart type="family">Deng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vasudha</namePart>
        <namePart type="family">Varadarajan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingxi</namePart>
        <namePart type="family">Yan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gunhee</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maarten</namePart>
        <namePart type="family">Sap</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Motahhare</namePart>
        <namePart type="family">Eslami</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>Explanations are often promoted as tools for transparency, but they can also foster blind trust; users may assume reasoning is correct whenever model outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT) explanations in multimodal moral scenarios by systematically perturbing reasoning chains and manipulating delivery tones. Specifically, we perturb reasoning chains generated by vision-language models (VLMs) with three error types (omissions, contradictions, hallucinations) and measure their effects on user trust and error detection through a study with 800 participants, alongside a parallel detection task with models. Our findings reveal two key effects: (1) users often equate trust with outcome agreement regardless of flaws in the model’s reasoning, and (2) confident tones suppress scrutiny while leaving agreement and self-reported trust largely unchanged. These results highlight how CoT explanations can simultaneously clarify and mislead in tandem, and point to user-side scrutiny, not just model-side faithfulness, as a critical dimension for calibrated trust in AI reasoning. All code will be released publicly upon acceptance.</abstract>
    <identifier type="citekey">park-etal-2026-critical</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2050/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>46688</start>
            <end>46708</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations
%A Park, Eunkyu
%A Deng, Wesley Hanwen
%A Varadarajan, Vasudha
%A Yan, Mingxi
%A Kim, Gunhee
%A Sap, Maarten
%A Eslami, Motahhare
%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 park-etal-2026-critical
%X Explanations are often promoted as tools for transparency, but they can also foster blind trust; users may assume reasoning is correct whenever model outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT) explanations in multimodal moral scenarios by systematically perturbing reasoning chains and manipulating delivery tones. Specifically, we perturb reasoning chains generated by vision-language models (VLMs) with three error types (omissions, contradictions, hallucinations) and measure their effects on user trust and error detection through a study with 800 participants, alongside a parallel detection task with models. Our findings reveal two key effects: (1) users often equate trust with outcome agreement regardless of flaws in the model’s reasoning, and (2) confident tones suppress scrutiny while leaving agreement and self-reported trust largely unchanged. These results highlight how CoT explanations can simultaneously clarify and mislead in tandem, and point to user-side scrutiny, not just model-side faithfulness, as a critical dimension for calibrated trust in AI reasoning. All code will be released publicly upon acceptance.
%U https://aclanthology.org/2026.emnlp-main.2050/
%P 46688-46708

Markdown (Informal)

[Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations](https://aclanthology.org/2026.emnlp-main.2050/) (Park et al., EMNLP 2026)

• Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations (Park et al., EMNLP 2026)

ACL

• Eunkyu Park, Wesley Hanwen Deng, Vasudha Varadarajan, Mingxi Yan, Gunhee Kim, Maarten Sap, and Motahhare Eslami. 2026. Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 46688–46708, Budapest, Hungary. Association for Computational Linguistics.