Showing cs.CLShow all
3 papers · 1 filter
cs.CL2024
Disentangling Length from Quality in Direct Preference Optimization
Ryan Park, Rafael Rafailov, Stefano Ermon +1
Reinforcement Learning from Human Feedback (RLHF) has been a crucial component in the recent success of Large Language Models. However, RLHF is know to exploit biases in human pref…
cs.CL2024
PERSONA: A Reproducible Testbed for Pluralistic Alignment
Louis Castricato, Nathan Lile, Rafael Rafailov +2
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the…
cs.CL2024
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
Jan-Philipp Fränken, Eric Zelikman, Rafael Rafailov +3
When prompting a language model (LM), users often expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoi…