arXiv:2607. 14285v1 Announce Type: cross Abstract: Safety alignment in LLMs aims to align models with human values, but which values take precedence when they conflict?
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 24758v1 Announce Type: new Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical deployment behaviors, a phenomenon known as alignment faking.
arXiv:2509. 05367v5 Announce Type: replace-cross Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe.
arXiv:2607. 10455v1 Announce Type: new Abstract: Autonomous CLI agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight.
arXiv:2607. 07184v1 Announce Type: cross Abstract: Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model.
Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model. Yet most evaluations provide limited evidence about how often undesired model behavior will occur in deployment: they generally have insufficient coverage, are unrepresentative, and are generally recognizable as tests.
arXiv:2607. 19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited.