Exploration with Principles for Diverse AI Supervision

Published: 28 Oct 2023, Last Modified: 28 Oct 2023MATH-AI 23 PosterEveryoneRevisionsBibTeX
Keywords: Language models, Math Reasoning, Instruction Tuning, Unsupervised Reinforcement Learning
TL;DR: We present an actor-critic based approach for generating diverse AI supervision.
Abstract: Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. Even state-of-the-art AI models like ChatGPT depend on fine-tuning through human demonstrations, demanding extensive human input and domain expertise. This strong reliance on human oversight poses a significant hurdle to the advancement of AI innovation. To address this limitation, we propose a novel paradigm termed Exploratory AI (EAI) aimed at autonomously generating high-quality training data. Drawing inspiration from the principles of unsupervised reinforcement learning (RL) pretraining, EAI achieves exploration within the natural language space. We accomplish this by harnessing large language models to assess the novelty of generated content. Our approach employs two key components: an actor that generates novel content and a critic that evaluates the generated content, offering critiques to guide the actor. Empirical evaluations demonstrate that EAI significantly boosts model performance on complex reasoning tasks, addressing the limitations of human-intensive supervision.
Submission Number: 17