相关论文: Output Supervision Can Obfuscate the Chain of Thou…

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…

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…

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…

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…

Chain-of-thought (CoT) reasoning provides a significant performance uplift to LLMs by enabling planning, exploration, and deliberation of their actions. CoT is also a powerful tool for monitoring the behaviours of these agents: when…

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…

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…

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…

As AI models are deployed with increasing autonomy, it is important to ensure they do not take harmful actions unnoticed. As a potential mitigation, we investigate Chain-of-Thought (CoT) monitoring, wherein a weaker trusted monitor model…

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…

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.…

Chain-of-thought (CoT) supervision can substantially improve transformer performance, yet the mechanisms by which models learn to follow and benefit from CoT remain poorly understood. We investigate these learning dynamics through the lens…

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…

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…

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…

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…

Chain-of-thought (CoT) reasoning not only enhances large language model performance but also provides critical insights into decision-making processes, marking it as a useful tool for monitoring model intent and planning. However, recent…

Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs). Although interpretable, its dependence on natural language limits the model's expressive bandwidth. Continuous…

We propose a variant of chain of thought (CoT) prompting called Program Trace Prompting that makes explanations more observable while preserving the power, generality and flexibility of CoT. In our approach, few-shot CoT demonstrations are…