Search Results for author:
Found 2 papers, 1 papers with code
Massive Editing for Large Language Models via Meta Learning
While large language models (LLMs) have enabled learning knowledge from the pre-training corpora, the acquired knowledge may be fundamentally incorrect or outdated over time, which necessitates rectifying the knowledge of the language model (LM) after the training.
Learning Rewards to Optimize Global Performance Metrics in Deep Reinforcement Learning
LR4GPM alternates between two phases: (1) learning a (possibly vector) reward function used to fit the performance metric, and (2) training a policy to optimize an approximation of this performance metric based on the learned rewards.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
