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.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
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: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:2606. 10740v1 Announce Type: new Abstract: Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation.