4 papers · 1 filter
Unsupervised Elicitation of Language Models
Jiaxin Wen, Zachary Ankner, Arushi Somani +10
To steer pretrained language models for downstream tasks, today's post-training paradigm relies on humans to specify desired behaviors. However, for models with superhuman capabili…
Language Models Learn to Mislead Humans via RLHF
Jiaxin Wen, Ruiqi Zhong, Akbir Khan +6
Language models (LMs) can produce errors that are hard to detect for humans, especially when the task is complex. RLHF, the most popular post-training method, may exacerbate this p…
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Jiaxin Wen, Vivek Hebbar, Caleb Larson +9
As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previou…
Spontaneous Reward Hacking in Iterative Self-Refinement
Jane Pan, He He, Samuel R. Bowman +1
Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference. In place of human u…