arXiv:2606. 15980v1 Announce Type: cross Abstract: Activation monitors-lightweight probes trained on a language model's internal representations-are an increasingly common layer in deployment safety stacks.
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint.
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.
The paper investigates how tool‑using language‑model agents can safely commit changes to infrastructure when external state may change between read and commit. By distinguishing invalidating races from predicate‑preserving and irrelevant ones, the authors evaluate three commit‑time guard granularities—global epoch, read‑set version, and semantic commit predicate—using a deterministic simulator and three quantized model families. The study finds that only the complete predicate guard consistently eliminates unsafe commits, while freshness‑based guards block a large proportion of benign races and model‑side signals fail to replace precise semantic enforcement.
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
arXiv:2606. 10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering.
The paper evaluates safety monitors by measuring recall only on prompts that the target model actually answers, rather than on all harmful prompts. Across several guard systems, recall at a 1% false‑positive rate drops sharply when focusing on answered prompts, with monitors catching refused requests 1.1–6.4 times more often than answered ones. Rewriting prompts to be less explicit dramatically increases compliance and reveals that many harmful requests slip past monitors, especially when phrasing is softened. Fine‑tuning guards on these rewritten prompts improves recall from 0.24 to 0.89 on answered requests and generalizes to unseen benchmarks.
arXiv:2606. 09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact.
arXiv:2607. 14570v1 Announce Type: new Abstract: AI software development agents are increasingly capable of modifying infrastructure and security critical systems, creating risks where an agent completes its assigned task while covertly weakening safeguards through actions such as broadening permissions, degrading logging, or introducing persistence mechanisms.
arXiv:2603. 28590v3 Announce Type: replace Abstract: Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs.
arXiv:2606. 11063v1 Announce Type: new Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model.
arXiv:2603.01209v3 Announce Type: replace Abstract: In CodeAct, language-model agents write Python that calls tools and use execution feedback to choose actions. Persistent runtimes preserve Python v...