Investigating CoT Monitorability in Large Reasoning Models
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks by engaging in extended reasoning before producing final answers. Beyond improving abilities, these detailed reasoning traces also create a new opportunity for AI safety, CoT Monitorability: monitoring potential model misbehavior, such as the use of shortcuts or sycophancy, through their chain-of-thought (CoT) during decision-making. However, two key fundamental challenges arise when attempting to build more effective monitors through CoT analysis. First, as prior research on CoT faithfulness has pointed out, models do not always truthfully represent their internal decision-making in the generated reasoning. Second, monitors themselves may be either overly sensitive or insufficiently sensitive, and can potentially be deceived by models' long, elaborate reasoning traces. In this paper, we present the first systematic investigation of the challenges and potential of CoT monitorability. Motivated by two fundamental challenges we mentioned before, we structure our study around two central perspectives: (i) verbalization: to what extent do LRMs faithfully verbalize the true factors guiding their decisions in the CoT, and (ii) monitor reliability: to what extent can misbehavior be reliably detected by a CoT-based monitor? Specifically, we provide empirical evidence and correlation analyses between verbalization quality, monitor reliability, and LLM performance across mathematical, scientific, and ethical domains. Then we further investigate how different CoT intervention methods, designed to improve reasoning efficiency or performance, will affect monitoring effectiveness. Finally, we propose MoME, a new paradigm in which LLMs monitor other models' misbehavior through their CoT and provide structured judgments along with supporting evidence.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning
As Large Reasoning Models (LRMs) are increasingly deployed, auditing their chain-of-thought (CoT) traces for safety becomes critical. Recent work has reported that monitorability--the degree to which CoT faithfully and i…
Reinforcement LearningMonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models
Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (…
Monitoring Monitorability
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 detecti…
Reinforcement LearningDecision MakingReasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
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. Howev…
Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
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…