Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Preprint
Abstract
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Recent work proposed advanced prompting techniques and the necessity of fine-tuning with high-quality data to augment LLMs' reasoning abilities. However, these approaches are inherently constrained by data availability and quality. In light of this, self-correction and self-learning emerge as viable solutions, employing strategies that allow LLMs to refine their outputs and learn from self-assessed rewards. Yet, the efficacy of LLMs in self-refining its response, particularly in complex reasoning and planning task, remains dubious. In this paper, we introduce AlphaLLM for the self-improvements of LLMs, which integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop, thereby enhancing the capabilities of LLMs without additional annotations. Drawing inspiration from the success of AlphaGo, AlphaLLM addresses the unique challenges of combining MCTS with LLM for self-improvement, including data scarcity, the vastness search spaces of language tasks, and the subjective nature of feedback in language tasks. AlphaLLM is comprised of prompt synthesis component, an efficient MCTS approach tailored for language tasks, and a trio of critic models for precise feedback. Our experimental results in mathematical reasoning tasks demonstrate that AlphaLLM significantly enhances the performance of LLMs without additional annotations, showing the potential for self-improvement in LLMs.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation2024
- A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning2024
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023
- A Survey of Reinforcement Learning Informed by Natural Language2019
- Intrinsically Motivated Reinforcement Learning2005
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002
- Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learningArtificial Intelligence, 1999