arXiv:2608.29118v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) on narrowly harmful datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM...
As large language models (LLMs) grow more capable, they are increasingly deployed in context-rich settings where task inputs are often accompanied by long, partially irrelevant context. In a controlled setting, we find that state-of-the-art models often appear robust to task-irrelevant context at the aggregate level: prepending it to benchmark questions causes little change in overall accuracy.
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
arXiv:2409. 02228v2 Announce Type: replace Abstract: When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change?
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:2607. 03478v1 Announce Type: new Abstract: Post-training of frontier language models is conducted on curated task suites, and inevitably leaves a distribution shift between training and deployment environments.
arXiv:2606. 23695v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds Large Language Models in external knowledge, yet current evaluations rely on discrete heuristics that suffer from ''epistemic blindness'' - failing to distinguish genuine contextual information extraction from parametric memory recall.
arXiv:2606. 07237v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question answering, diagnosis support, and report summarization.
arXiv:2601. 22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design.
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
The paper introduces FAB, an attack that uses meta‑learning to embed dormant adversarial behaviors into large language models (LLMs). These behaviors remain inactive until the model is finetuned by downstream users, at which point the model can exhibit unwanted actions such as unsolicited advertising, jailbreakability, or over‑refusal. FAB is shown to be effective across multiple LLMs and resilient to various finetuning settings.