Timezone: »

 
Spotlight
Co-training Improves Prompt-based Learning for Large Language Models
Hunter Lang · Monica Agrawal · Yoon Kim · David Sontag

Tue Jul 19 08:20 AM -- 08:25 AM (PDT) @ Room 301 - 303
in APP: Language, Speech and Dialog »

We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data. While prompting has emerged as a promising paradigm for few-shot and zero-shot learning, it is often brittle and requires much larger models compared to the standard supervised setup. We find that co-training makes it possible to improve the original prompt model and at the same time learn a smaller, downstream task-specific model. In the case where we only have partial access to a prompt model (e.g., output probabilities from GPT-3 (Brown et al., 2020)) we learn a calibration model over the prompt outputs. When we have full access to the prompt model's gradients but full finetuning remains prohibitively expensive (e.g., T0 (Sanh et al., 2021)), we learn a set of soft prompt continuous vectors to iteratively update the prompt model. We find that models trained in this manner can significantly improve performance on challenging datasets where there is currently a large gap between prompt-based learning and fully-supervised models.

Keywords: APP: Language, Speech and Dialog · DL: Everything Else · MISC: Unsupervised and Semi-supervised Learning · MISC: Transfer, Multitask and Meta-learning

Author Information

Hunter Lang (MIT)
Monica Agrawal (Massachusetts Institute of Technology)
Yoon Kim (Harvard University)
David Sontag (Massachusetts Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors