4 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)…
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
Mohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi +2
Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions converge in predictable token counts, re…
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…
Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
Mina Taraghi, Yann Pequignot, Amin Nikanjam +2
Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks. Prior work shows that even fine-tuning on benign dat…