Large “instruction-tuned” language models (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 limited in quantity, diversity, and creativity, therefore hindering the generality of the tuned model. We introduce S ELF -I NSTRUCT , a framework for improving the instruction-following capabilities of pretrained language models by bootstrapping oﬀ its own generations. Our pipeline generates instruction, input, and output samples from a language model, then prunes them before using them to ﬁnetune the original model.
2022: Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, Hannaneh Hajishirzi
To leave or reply to comments, please download free Podbean or
To leave or reply to comments, please download free Podbean App.