Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

arXiv:2404.12253v1 Announce Type: new
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 …

abstract advanced arxiv capabilities cs.cl data fine-tuning however imagination improvement language language models large language large language models llms planning prompting quality quality data reasoning searching self-improvement struggle tasks type via work