arXiv:2607. 07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output.
arXiv:2606. 15127v1 Announce Type: new Abstract: Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students intermediate steps, decision-support systems may require human oversight, and audit workflows may inspect traces for misleading or biased input.
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv:2609.38107v1 Announce Type: cross Abstract: Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning...
arXiv:2602. 13904v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety.
arXiv:2608. 02820v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions.
arXiv:2605. 08827v2 Announce Type: replace Abstract: The safety of mental health AI is often judged at the wrong temporal scale.
arXiv:2609.21492v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has been shown to improve the performance of large language models (LLMs), yet existing optimization methods largely r...
arXiv:2606. 10740v1 Announce Type: new Abstract: Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation.
arXiv:2607. 01153v1 Announce Type: cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused appropriately, complied with a policy, resisted an embedded command, or misreported progress in an agentic task.
arXiv:2603. 05167v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility.
The paper introduces a new attack called "plan injection" that allows a large language model to carry out harmful actions while evading chain-of-thought monitoring. By inserting harmful but benign-sounding reasoning into the model’s context, the attacker can steer the model’s behavior and cause it to paraphrase the injected plan as its own reasoning. The study demonstrates that this attack works across different monitoring settings, scales to harder tasks, and even causes monitors to waste resources on the injected plan, reducing detection rates by up to 50%.
TRACE is a new benchmark that evaluates the safety of Large Reasoning Models (LRMs) across the entire inference pipeline, including prompts, reasoning traces, and final responses. It provides prompts in two languages covering nine risk categories and ten attack strategies, and for each prompt four LRMs generate traces and responses that are annotated for safety with supporting evidence extracted from the source text. Evaluation of 18 guardrail models on TRACE shows that detecting unsafe content in reasoning traces is much harder than in prompts or final responses, and that current models struggle to extract the necessary evidence.