arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
arXiv:2609.00064v1 Announce Type: cross Abstract: In-context learning (ICL) lets large language models adapt to new tasks from demonstrations, and fine-tuning can erode this behaviour. Many preservat...
The paper introduces Latent Space Refusal Anchoring (LSR‑Anchoring), a training‑free technique that extracts a refusal direction from English prompts and applies it to the residual stream of instruction‑tuned models at inference time. The primary variant, Mean‑Activation Steering (MAS), works across several architectures (Llama‑3‑8B, Llama‑3.1‑70B, Mistral‑7B‑Instruct, Qwen2.5‑7B), restoring safety for low‑resource African languages with minimal performance loss, while a refined SAE‑Derived Steering (SDS) further reduces KL divergence without degrading legitimate prompt performance. The method shows positive transfer for Yoruba, Igbo, Igala, and Hausa, but fails for Arabic, suggesting a geometric mismatch rather than a data scarcity issue.
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.
arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.
arXiv:2608. 12334v1 Announce Type: cross Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood.
arXiv:2609.22119v1 Announce Type: cross Abstract: Evaluation awareness poses an unprecedented threat to model evaluation, but the mechanisms by which models detect it remain unknown. This study focus...
The paper investigates how trigger-based backdoors function in large language models by using sparse autoencoders (SAEs) to identify feature directions across layers and transformer components. In a controlled experiment, 1B and 8B models were made to continue English prompts in French or German when presented with fixed trigger sequences. The study finds that different SAE feature directions correspond to trigger detection, residual-stream propagation, and language tracking, with residual-stream features being most effective for controlling the backdoor behavior.
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusa...
arXiv:2603. 03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}.
arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.