Efficient Safety Alignment of Language Models via Latent Personality Traits
arXiv:2607.07918v1 Announce Type: cross Abstract: Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives…
Read the full articleYou might also wanna read
Adversarial Poetry Functions as Universal Jailbreak Technique for Large Language Models
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Acros
arxiv.org·7mo ago
Training Large Language Models for Honesty Through Self-Reported Confessions
Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidenc
arxiv.org·6mo agoJavelinGuard: Low-Cost Transformer Architectures for LLM Security
We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language
JaiLIP: A new image-based jailbreak attack method for Vision-Language Models
Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignm
arxiv.org·12d agoHow catastrophic is your LLM?
A new framework provides a statistical method for estimating the likelihood of catastrophic failures in large language models in adversarial
Research Reveals LLMs Contain Built-In Persona Subnetworks Without External Training
Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopt
arxiv.org·4mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.