Large Language Model
Multi-turn Reinforcement Learning from Preference Human Feedback
In the tabular setting, we present a novel mirror-descent-based policy optimization algorithm for the general multi-turn preference-based RL problem, and prove its convergence to Nash equilibrium.
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass Ethan Shen Alan Fan Sarah Pratt Jae Sung Park Matthew Wallingford Sham Kakade Ari Holtzman Ranjay Krishna
Many applications today provide users with multiple auto-complete drafts as they type, including GitHub's code completion, Gmail's smart compose, and Apple's messaging auto-suggestions.
Improving Generalization and Convergence by Enhancing Implicit Regularization Mingze Wang 1,3, Jinbo Wang 1, 3 Haotian He1,3 Zilin Wang 1
We show that IRE can be practically incorporated with generic base optimizers without introducing significant computational overload.
Knowledge Circuits in Pretrained Transformers
In this paper, we delve into the computation graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge.
MambaLRP: ExplainingSelectiveStateSpace SequenceModels
To foster their reliable use in real-world scenarios, it is crucial to augment their transparency.