[2503.08679] Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
Skip to main content
Search arXiv
Press Enter to search · Advanced search
-->
Computer Science > Artificial Intelligence
arXiv:2503.08679 (cs)
[Submitted on 11 Mar 2025 (v1), last revised 16 Jun 2026 (this version, v6)]
Title:Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
Authors:Iván Arcuschin, Jett Janiak, Robert Krzyzanowski, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy<br>View a PDF of the paper titled Chain-of-Thought Reasoning In The Wild Is Not Always Faithful, by Iv\'an Arcuschin and 5 other authors
View PDF<br>HTML (experimental)
Abstract:Recent studies indicate that when faced with explicit biases in prompts, models often omit mentioning these biases in their Chain-of-Thought (CoT) output, revealing that verbalized reasoning can give an incorrect picture of how models arrive at conclusions (unfaithfulness). In this work, we show that unfaithful CoT also occurs on naturally worded, non-adversarial prompts without adding artificial biases or editing model outputs. We find that when separately presented with the questions "Is X bigger than Y?" and "Is Y bigger than X?", models sometimes produce superficially coherent arguments to justify systematically answering Yes to both or No to both, despite the contradiction. We present preliminary evidence that this is due to models' implicit biases towards Yes or No, labeling this Implicit Post-Hoc Rationalization. Our results reveal rates up to 13% for production models, and while frontier models are more faithful, none are entirely so, including thinking models like DeepSeek R1 (0.37%) and Sonnet 3.7 with thinking (0.04%). We also investigate Unfaithful Illogical Shortcuts, where models use subtly illogical reasoning to make speculative answers to hard math problems seem rigorously proven. Our findings indicate that while CoT can be useful for assessing outputs, it is not a complete account of the internal process that produced the model's answer and should be used with caution in agentic or safety-critical settings.
Comments:<br>Published at the 43rd International Conference on Machine Learning (ICML 2026)
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as:<br>arXiv:2503.08679 [cs.AI]
(or<br>arXiv:2503.08679v6 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2503.08679
Focus to learn more
arXiv-issued DOI via DataCite
Submission history<br>From: Iván Arcuschin [view email]<br>[v1]<br>Tue, 11 Mar 2025 17:56:30 UTC (4,311 KB)
[v2]<br>Thu, 13 Mar 2025 17:49:58 UTC (4,348 KB)
[v3]<br>Wed, 19 Mar 2025 19:20:42 UTC (4,349 KB)
[v4]<br>Tue, 17 Jun 2025 17:59:57 UTC (2,337 KB)
[v5]<br>Fri, 29 May 2026 17:38:22 UTC (2,378 KB)
[v6]<br>Tue, 16 Jun 2026 17:36:22 UTC (2,378 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Chain-of-Thought Reasoning In The Wild Is Not Always Faithful, by Iv\'an Arcuschin and 5 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.AI
next >
new<br>recent<br>| 2025-03
Change to browse by:
cs<br>cs.CL<br>cs.LG
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .
Which authors of this paper are endorsers?...