8 papers
Efficient Safety Alignment of Language Models via Latent Personality Traits
Mohamed Amine Merzouk, Nolan Smyth, Damiano Fornasiere +3
Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Latent Adversarial Training (LAT)…
vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
Khanh D. Nguyen, Hung T. Ho, Chinh T. Nguyen +5
Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware on which robots actually run.…
Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning
Isabella Luong, Joyee Chen, Arturs Kanepajs +5
Evaluating animal welfare reasoning in LLMs remains an open challenge despite rapid deployment in consumer and professional contexts where welfare considerations appear implicitly…
FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments
Astha Mehta, Niruthiha Selvanayagam, Cedric Lam +10
An attacker can split a malicious goal into sub-prompts that each look benign on their own and only become harmful in combination. Existing LLM safety benchmarks evaluate prompts o…
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
Linh Le, David Williams-King, Mohamed Amine Merzouk +2
Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerab…
Diagnosing Pathological Chain-of-Thought in Reasoning Models
Manqing Liu, David Williams-King, Ida Caspary +5
Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT reasoning may exhibit failure m…