arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while ret...
arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.
arXiv:2609.15886v1 Announce Type: new Abstract: Large language models (LLMs) often learn both desirable and undesirable properties during post-training. We study whether midtraining, an earlier train...
arXiv:2606. 24267v1 Announce Type: cross Abstract: While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing.
arXiv:2606. 24267v2 Announce Type: replace-cross Abstract: While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing.
arXiv:2606. 30252v1 Announce Type: new Abstract: Inoculation prompting is a selective generalization technique used against Emergent Misalignment.
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...
arXiv:2508. 06249v3 Announce Type: replace Abstract: Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EM): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target domain.
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. 02211v1 Announce Type: cross Abstract: Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer.
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}.
The paper introduces Semantic Overlays, a steering technique that adds non‑textual annotations to a language model’s input by applying learned adapters at specific prefill positions. These overlays create an out‑of‑band channel that encodes span identity and complex semantics, enabling the model to interpret marked text differently—such as rewriting code in a specified language or ignoring executable instructions. Experiments show that Semantic Overlays dramatically reduce prompt‑injection success rates while preserving model utility and readability of marked spans.