arXiv:2608. 03201v1 Announce Type: new Abstract: Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs.
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:2606. 29171v1 Announce Type: cross Abstract: While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training data shapes the high-level behavioral decisions a model learns to make.
arXiv:2608. 14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this promise, i.
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
arXiv:2606. 18322v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features.
arXiv:2606. 32038v1 Announce Type: cross Abstract: When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation?
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
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:2606. 28153v1 Announce Type: cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood.
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:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.