arXiv:2605. 24583v3 Announce Type: replace Abstract: Comparing a model's internal activations before and after alignment is a natural way to ask what safety training changes: one forms the matrix of paired aligned-minus-base activations on safety-relevant inputs and reads off its effective rank or top direction.
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
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.
arXiv:2606. 31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts.
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
arXiv:2607. 01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable.
arXiv:2608. 04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence.
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation process can also degrade alignment properties that were present in the source model.
arXiv:2607. 07023v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning.
arXiv:2607. 18114v1 Announce Type: cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer.
arXiv:2511. 00382v2 Announce Type: replace-cross Abstract: Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks.
arXiv:2608. 11583v1 Announce Type: new Abstract: Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters.
arXiv:2605. 27681v2 Announce Type: replace-cross Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences.