Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Model

no code implementations • 3 Jul 2024 • Xia Hou, QiFeng Li, Jian Yang, Tongliang Li, Linzheng Chai, Xianjie Wu, Hangyuan Ji, Zhoujun Li, Jixuan Nie, Jingbo Dun, Wenfeng Song

In this paper, we present a novel framework named R2S that leverages the CoD-Chain of Dialogue logic to guide large language models (LLMs) in generating knowledge-intensive multi-turn dialogues for instruction tuning.

Language Modelling Large Language Model