LLMs-as-instructors : Learning from errors toward automating model improvement

• Main Authors: YING, Jiahao, LIN, Mingbao, CAO, Yixin, TANG, Wei, WANG, Bo, SUN, Qianru, HUANG, Xuanjing, YAN, Shuicheng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Large Language Models; LLM; Learning from errors; Model training; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/9440
• Institution: Singapore Management University

This paper introduces the innovative "LLMs-as-Instructors'' framework, which leverages the advanced Large Language Models (LLMs) to autonomously enhance the training of smaller target models. Inspired by the theory of "Learning from Errors'', this framework employs an i...