Better Alignment with Instruction Back-and-Forth Translation
Abstract
We propose a new method, instruction back-and-forth translation, to construct high-quality synthetic data grounded in world knowledge for aligning large language models (LLMs).
https://arxiv.org/abs/2408.04614 #LLM
Abstract
We propose a new method, instruction back-and-forth translation, to construct high-quality synthetic data grounded in world knowledge for aligning large language models (LLMs).
https://arxiv.org/abs/2408.04614 #LLM