8 citations · 12 across the 5 of their papers we have counts for
6 papers
Trust the Critic More
Kaiyue Wen, Luke Bailey, Arvind Mahankali +1
Standard language model RL algorithms credit every token of a long rollout with the same advantage determined by the terminal reward. Actor-critic methods can provide finer-grained…
Pseudo-Formalization for Automatic Proof Verification
Slim Barkallah, Luke Bailey, Kaiyue Wen +2
Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to…
Synthetic Data for any Differentiable Target
Tristan Thrush, Sung Min Park, Herman Brunborg +5
What are the limits of controlling language models via synthetic training data? We develop a reinforcement learning (RL) primitive, the Dataset Policy Gradient (DPG), which can pre…
Scaling Self-Play with Self-Guidance
Luke Bailey, Kaiyue Wen, Kefan Dong +2
LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve together. However, in…
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Sam Toyer, Olivia Watkins, Ethan Adrian Mendes +9
While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to prompt injection attacks: malicious third party prompts that su…
Image Hijacks: Adversarial Images can Control Generative Models at Runtime
Luke Bailey, Euan Ong, Stuart Russell +1
Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images tha…