Self-Instruct: Aligning Language Models with Self-Generated Instructions

Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is often limited in quantity, diversity, and creativity, therefore hindering the generality of the tuned model. We introduce SELF-INSTRUCT, a framework for improving the instruction-following capabilities of pretrained language models by bootstrapping off their own generations. Our pipeline generates instructions, input, and output samples from a language model, then filters invalid or similar ones before using them to finetune the original model. Applying our method to the vanilla GPT3, we demonstrate a 33% absolute improvement over the original model on SUPER-NATURALINSTRUCTIONS, on par with the performance of InstructGPT 001 , 1 which was trained with private user data and human annotations. For further evaluation, we curate a set of expert-written instructions for novel tasks, and show through human evaluation that tuning GPT3 with SELF-INSTRUCT outperforms using existing public instruction datasets by a large margin, leaving only a 5% absolute gap behind InstructGPT 001 . SELF-INSTRUCT provides an almost annotation-free method for aligning pretrained language models with instructions, and we release our large synthetic dataset to facilitate future studies on instruction tuning. 2 Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. In Advances in Neural Information Processing Systems (NeurIPS) Workshop on Energy Efficient Machine Learning and Cognitive Computing.