@inproceedings{kim-lee-2026-causally,
title = "Causally Redundant Reasoning: A Dual-Disruption Test Framework for Measuring Shortcut Tendencies in Chain-of-Thought",
author = "Kim, Jiwoo and
Lee, Jongwuk",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2233/",
doi = "10.18653/2026.findings-emnlp.2233",
pages = "47788--47820",
ISBN = "979-8-89176-462-0",
abstract = "A chain-of-thought (CoT) rationale can be coherent and answer-consistent while remaining causally unused. We call this phenomenon shortcut reasoning: the model appears to reason through CoT, but its answer does not depend on the expressed trace. We formalize shortcut reasoning as causal redundancy and propose a dual-disruption framework for measuring shortcut tendencies in CoT by testing two complementary aspects of causal explanation: necessity and sufficiency. We operationalize them as two behavioral signals: whether the answer changes under CoT disruption, and whether the answer can be recovered from the CoT after masking the original input. We instantiate this framework with CORD (Causal Redundancy of Reasoning via Disruption), an instance-level score that combines both signals. The two axes reduce complementary ambiguities in single-axis tests: answer preservation under CoT disruption can reflect shortcut use or redundant truthful reasoning, while early answer recovery can reflect shortcut use or a compact truthful rationale. Across 6 models and 2 datasets, CORD reveals a training-paradigm effect: R1-Distill models exhibit roughly twice the shortcut tendency of non-distilled models, while the two axes capture related but distinct signals. Together, these results motivate joint tests of necessity and sufficiency for detecting shortcut tendencies that can remain hidden behind correct answers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-lee-2026-causally">
<titleInfo>
<title>Causally Redundant Reasoning: A Dual-Disruption Test Framework for Measuring Shortcut Tendencies in Chain-of-Thought</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiwoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jongwuk</namePart>
<namePart type="family">Lee</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>A chain-of-thought (CoT) rationale can be coherent and answer-consistent while remaining causally unused. We call this phenomenon shortcut reasoning: the model appears to reason through CoT, but its answer does not depend on the expressed trace. We formalize shortcut reasoning as causal redundancy and propose a dual-disruption framework for measuring shortcut tendencies in CoT by testing two complementary aspects of causal explanation: necessity and sufficiency. We operationalize them as two behavioral signals: whether the answer changes under CoT disruption, and whether the answer can be recovered from the CoT after masking the original input. We instantiate this framework with CORD (Causal Redundancy of Reasoning via Disruption), an instance-level score that combines both signals. The two axes reduce complementary ambiguities in single-axis tests: answer preservation under CoT disruption can reflect shortcut use or redundant truthful reasoning, while early answer recovery can reflect shortcut use or a compact truthful rationale. Across 6 models and 2 datasets, CORD reveals a training-paradigm effect: R1-Distill models exhibit roughly twice the shortcut tendency of non-distilled models, while the two axes capture related but distinct signals. Together, these results motivate joint tests of necessity and sufficiency for detecting shortcut tendencies that can remain hidden behind correct answers.</abstract>
<identifier type="citekey">kim-lee-2026-causally</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.2233</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2233/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>47788</start>
<end>47820</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Causally Redundant Reasoning: A Dual-Disruption Test Framework for Measuring Shortcut Tendencies in Chain-of-Thought
%A Kim, Jiwoo
%A Lee, Jongwuk
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kim-lee-2026-causally
%X A chain-of-thought (CoT) rationale can be coherent and answer-consistent while remaining causally unused. We call this phenomenon shortcut reasoning: the model appears to reason through CoT, but its answer does not depend on the expressed trace. We formalize shortcut reasoning as causal redundancy and propose a dual-disruption framework for measuring shortcut tendencies in CoT by testing two complementary aspects of causal explanation: necessity and sufficiency. We operationalize them as two behavioral signals: whether the answer changes under CoT disruption, and whether the answer can be recovered from the CoT after masking the original input. We instantiate this framework with CORD (Causal Redundancy of Reasoning via Disruption), an instance-level score that combines both signals. The two axes reduce complementary ambiguities in single-axis tests: answer preservation under CoT disruption can reflect shortcut use or redundant truthful reasoning, while early answer recovery can reflect shortcut use or a compact truthful rationale. Across 6 models and 2 datasets, CORD reveals a training-paradigm effect: R1-Distill models exhibit roughly twice the shortcut tendency of non-distilled models, while the two axes capture related but distinct signals. Together, these results motivate joint tests of necessity and sufficiency for detecting shortcut tendencies that can remain hidden behind correct answers.
%R 10.18653/2026.findings-emnlp.2233
%U https://aclanthology.org/2026.findings-emnlp.2233/
%U https://doi.org/10.18653/2026.findings-emnlp.2233
%P 47788-47820
Markdown (Informal)
[Causally Redundant Reasoning: A Dual-Disruption Test Framework for Measuring Shortcut Tendencies in Chain-of-Thought](https://aclanthology.org/2026.findings-emnlp.2233/) (Kim & Lee, Findings 2026)
ACL