Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
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)…
cs.LG2026
LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
Lennart Wachowiak, Scott D. Blain, David Williams-King +1
LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=120) across four decision-maki…