Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

The paper introduces a boundary-aware self‑distillation framework for controlled large language model safety refusal, addressing the need for different refusal boundaries within the same topic. It combines controlled topic generation, coverage repair, in‑distribution compensation data, and harmful‑benign pairs to train and evaluate refusal behavior. Experiments on Qwen3‑8B show that escalating retries dramatically improve target‑domain refusal rates while reducing unsafe responses, though they also increase over‑refusal, highlighting the trade‑off between safety and usability.

Helping people when they need it most

How we think about safety for users experiencing mental or emotional distress, the limits of today’s systems, and the work underway to refine them.

Democratizing AI Safety with RiskRubric.ai

OpenAI’s commitment to child safety: adopting safety by design principles

The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models

arXiv:2605. 05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems

SafeTutors is a benchmark designed to evaluate both safety and pedagogical effectiveness of AI tutoring systems across mathematics, physics, and chemistry. It introduces a risk taxonomy of 11 harm dimensions and 48 sub‑risks based on learning‑science literature, focusing on issues such as answer over‑disclosure, misconception reinforcement, and loss of scaffolding. The study finds that all tested models exhibit broad harms, that larger scale does not mitigate these issues, and that multi‑turn interactions significantly increase pedagogical failures from 17.7% to 77.8%.

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

The paper investigates how large language models balance helpfulness and safety by refusing harmful queries while responding to benign ones. It decomposes safety-tuning responses into a boilerplate refusal statement and a rationale, finding that the statement causes false refusals by relying on superficial cues. Training on rationales alone reduces false refusals without compromising safety performance, suggesting that fine‑grained safety supervision is essential for better alignment.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.

AI Persuasion as a Threat to Human Control

arXiv:2609.14796v1 Announce Type: new Abstract: The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied. Now that persuasion a...

Frontier AI regulation: Managing emerging risks to public safety

Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators

arXiv:2606. 07874v1 Announce Type: new Abstract: LLMs-as-judges are the only way to evaluate safety at scale.

No One Model Catches Every Harm: Benchmarking Content Moderation Across Safety Scenarios

arXiv:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adver...