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

By Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, Hannaneh Hajishirzi. Annual Meeting of the Association for Computational Linguistics, 2022

3,444 citations recorded by the source corpus.

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, 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 pre-trained language models with instructions, and we release our large synthetic dataset to facilitate future studies on instruction tuning.

Subfields: Artificial Intelligence, Large Language Models, Alignment & RLHF

View Paper: https://arxiv.org/abs/2212.10560

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Jianfeng Gao
  3. Luke S. Zettlemoyer
  4. Yejin Choi
  5. Percy Liang
  6. Graham Neubig
  7. Noah A. Smith
  8. Quoc V. Le

In Large Language Models

  1. Luke S. Zettlemoyer
  2. Hinrich Schütze
  3. Yejin Choi
  4. Noah A. Smith
  5. Jianfeng Gao
  6. Timo Schick
  7. Michael Lewis
  8. Graham Neubig

In Alignment & RLHF

  1. Luke S. Zettlemoyer
  2. Jianfeng Gao
  3. Ari Holtzman
  4. Tim Dettmers
  5. Artidoro Pagnoni
  6. Tianyi Zhang
  7. Noah A. Smith
  8. Yu Meng

Citations in the corpus