Search Results for author:
Found 4 papers, 1 papers with code
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
We investigate the setup of "Parameter Efficient Reinforcement Learning" (PERL), in which we perform reward model training and reinforcement learning using LoRA.
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences.
Conversational Recommendation as Retrieval: A Simple, Strong Baseline
Conversational recommendation systems (CRS) aim to recommend suitable items to users through natural language conversation.
Prose for a Painting
Painting captions are often dry and simplistic which motivates us to describe a painting creatively in the style of Shakespearean prose.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
