Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
Narmeen Oozeer, Luke Marks, Shreyans Jain +2
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of…
cs.LG2024
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
Maya Pavlova, Erik Brinkman, Krithika Iyer +7
Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automate…