7 papers
ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
Hongjue Zhao, Haosen Sun, Jiangtao Kong +8
Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations at inference time…
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Salman Rahman, Liwei Jiang, James Shiffer +7
Multi-turn interactions with language models (LMs) pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work…
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
Jing-Jing Li, Valentina Pyatkin, Max Kleiman-Weiner +7
The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect…
Diverging Preferences: When do Annotators Disagree and do Models Know?
Michael JQ Zhang, Zhilin Wang, Jena D. Hwang +6
We examine diverging preferences in human-labeled preference datasets. We develop a taxonomy of disagreement sources spanning ten categories across four high-level classes and find…
AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
Ximing Lu, Melanie Sclar, Skyler Hallinan +8
Creativity has long been considered one of the most difficult aspect of human intelligence for AI to mimic. However, the rise of Large Language Models (LLMs), like ChatGPT, has rai…
Can Language Models Reason about Individualistic Human Values and Preferences?
Liwei Jiang, Taylor Sorensen, Sydney Levine +1
Recent calls for pluralistic alignment emphasize that AI systems should address the diverse needs of all people. Yet, efforts in this space often require sorting people into fixed…