Search Results for author:
Found 4 papers, 2 papers with code
A StrongREJECT for Empty Jailbreaks
We show that our new grading scheme better accords with human judgment of response quality and overall jailbreak effectiveness, especially on the sort of low-quality responses that contribute the most to over-estimation of jailbreak performance on existing benchmarks.
Leading the Pack: N-player Opponent Shaping
We evaluate on over 4 different environments, varying the number of players from 3 to 5, and demonstrate that model-based OS methods converge to equilibrium with better global welfare than naive learning.
JaxMARL: Multi-Agent RL Environments in JAX
This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL.
Retrospective on the 2021 BASALT Competition on Learning from Human Feedback
The goal of the competition was to promote research towards agents that use learning from human feedback (LfHF) techniques to solve open-world tasks.
