REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features

arXiv:2606.13720v1 Announce Type: new Abstract: Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the

<!-- SC_OFF --><div class="md"><p>I set out to test whether AAVE-coded (African American English Vernacular) prompts cause MoE language models to route, deliberate, and respond

arXiv:2606.17257v1 Announce Type: cross Abstract: Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing

arXiv:2511.21399v3 Announce Type: replace-cross Abstract: Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety

arXiv:2605.21706v1 Announce Type: new Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their

arXiv:2608.08032v1 Announce Type: new Abstract: Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply

arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce

arXiv:2610.24287v1 Announce Type: new Abstract: Search-augmented language models increasingly serve as long-horizon research agents, yet most open training methods assume a fixed