Keywords: Instruction-Following, Reinforcement Learning from Human Feedback, Artificial General Intelligence, Large Language Models
TL;DR: We propose and validate a simulator that enables research on learning from human feedback at a low cost.
Abstract: Large language models (LLMs) such as ChatGPT have seen widespread adoption due to their ability to follow user instructions well.
Developing these LLMs involves a complex yet poorly understood workflow requiring training with human feedback. Replicating and understanding this instruction-following process faces three major challenges: the high cost of data collection, the lack of trustworthy evaluation, and the absence of reference method implementations. We address these bottlenecks with AlpacaFarm, a simulator that enables research and development for learning from feedback at a low cost. First, we design LLM based simulator for human feedback that is 45x cheaper than crowdworkers and displays high agreement with humans. Second, we identify an evaluation dataset representative of real-world instructions and propose an automatic evaluation procedure. Third, we contribute reference implementations for several methods (PPO, best-of-n, expert iteration, among others) that learn from pairwise feedback. Finally, as an end-to-end validation of AlpacaFarm, we train and evaluate eleven models on 10k pairs of human feedback and show that rankings of models trained in AlpacaFarm match rankings of models trained on human data. As a demonstration of the research possible in AlpacaFarm, we find that methods that use a reward model can substantially improve over supervised fine-tuning and that our reference PPO implementation leads to a +10% win-rate improvement against Davinci003.
Supplementary Material: pdf
Submission Number: 5730
Loading