English
Related papers

Related papers: CoT Red-Handed: Stress Testing Chain-of-Thought Mo…

200 papers

While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on "unfaithfulness" has cast doubt on its reliability. These findings highlight an important failure mode, particularly when CoT acts as a post-hoc…

Artificial Intelligence · Computer Science 2025-07-08 Scott Emmons , Erik Jenner , David K. Elson , Rif A. Saurous , Senthooran Rajamanoharan , Heng Chen , Irhum Shafkat , Rohin Shah

Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignment monitoring: when models articulate their reasoning…

Cryptography and Security · Computer Science 2025-10-24 Artur Zolkowski , Wen Xing , David Lindner , Florian Tramèr , Erik Jenner

Chain-of-thought (CoT) monitoring is one of the most promising tools we have for detecting model misbehavior, but its effectiveness depends on models faithfully externalizing their reasoning. Motivated by this vulnerability, we study…

Machine Learning · Computer Science 2026-05-18 Reilly Haskins , Bilal Chughtai , Joshua Engels

Observability into the decision making of modern AI systems may be required to safely deploy increasingly capable agents. Monitoring the chain-of-thought (CoT) of today's reasoning models has proven effective for detecting misbehavior.…

As AI systems approach dangerous capability levels where inability safety cases become insufficient, we need alternative approaches to ensure safety. This paper presents a roadmap for constructing safety cases based on chain-of-thought…

Machine Learning · Computer Science 2025-10-23 Julian Schulz

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows…

Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully…

Chain-of-thought (CoT) monitoring is proposed as a method for overseeing the internal reasoning of language-model agents. Prior work has shown that when models are explicitly informed that their reasoning is being monitored, or are…

Cryptography and Security · Computer Science 2026-03-19 Thomas Jiralerspong , Flemming Kondrup , Yoshua Bengio

Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT…

Artificial Intelligence · Computer Science 2026-03-09 Chen Yueh-Han , Robert McCarthy , Bruce W. Lee , He He , Ian Kivlichan , Bowen Baker , Micah Carroll , Tomek Korbak

Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model…

Computation and Language · Computer Science 2026-05-28 Eric Onyame , Runtao Zhou , Kowshik Thopalli , Bhavya Kailkhura , Chirag Agarwal

While Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety, this opportunity could be lost through shifts in training practices or model architecture. To help preserve monitorability, we propose a pragmatic way to…

Machine Learning · Computer Science 2025-10-29 Scott Emmons , Roland S. Zimmermann , David K. Elson , Rohin Shah

Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest, such as test-hacking behavior during code generation. In this paper, we use information-theoretic…

Machine Learning · Computer Science 2026-02-23 Usman Anwar , Tim Bakker , Dana Kianfar , Cristina Pinneri , Christos Louizos

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models. We show that we can monitor a frontier reasoning…

Artificial Intelligence · Computer Science 2025-03-18 Bowen Baker , Joost Huizinga , Leo Gao , Zehao Dou , Melody Y. Guan , Aleksander Madry , Wojciech Zaremba , Jakub Pachocki , David Farhi

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Computation and Language · Computer Science 2025-10-17 Shiyuan Guo , Henry Sleight , Fabien Roger

Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This…

Machine Learning · Computer Science 2025-12-02 Austin Meek , Eitan Sprejer , Iván Arcuschin , Austin J. Brockmeier , Steven Basart

AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to…

Artificial Intelligence · Computer Science 2025-12-10 Matt MacDermott , Qiyao Wei , Rada Djoneva , Francis Rhys Ward

Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…

Machine Learning · Computer Science 2026-03-10 Nikolaus Howe , Micah Carroll

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We…

Artificial Intelligence · Computer Science 2026-05-13 Wenkai Li , Fan Yang , Ananya Hazarika , Shaunak A. Mehta , Koichi Onoue

OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors…

Machine Learning · Computer Science 2025-11-18 Jacob Drori , Luke Marks , Bryce Woodworth , Alex Cloud , Alexander Matt Turner

Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which a model's CoT helps us oversee the model - the…

Machine Learning · Computer Science 2026-04-01 Max Kaufmann , David Lindner , Roland S. Zimmermann , and Rohin Shah
‹ Prev 1 2 3 10 Next ›