Guess the Instruction! Making Language Models Stronger Zero-Shot LearnersDownload PDF


22 Sept 2022, 12:38 (modified: 11 Nov 2022, 07:57)ICLR 2023 Conference Blind SubmissionReaders: Everyone
Keywords: natural language processing, zeroshot language models, large language models
TL;DR: We introduce Flipped Learning, a meta-training method that computes the likelihood of the task instruction given input instance and label.
Abstract: Meta-training, which fine-tunes the language model (LM) on various downstream tasks by maximizing the likelihood of the target label given the task instruction and input instance, has improved the zero-shot task generalization performance. However, meta-trained LMs still struggle to generalize to challenging tasks containing novel labels unseen during meta-training. In this paper, we propose Flipped Learning, an alternative method of meta-training which trains the LM to generate the task instruction given the input instance and label. During inference, the LM trained with Flipped Learning, referred to as Flipped, selects the label option that is most likely to generate the task instruction. On 14 tasks of the BIG-bench benchmark, the 3B-sized Flipped outperforms 4 times larger zero-shot T0-11B (Sanh et al, 2021) and even a 60 times larger 3-shot GPT-3 (175B) (Brown et al, 2020) on average by 1.8% and 3.1%, respectively. Flipped gives particularly large improvements on unseen labels, outperforming T0-11B by up to +20% average F1 score. This indicates that the strong task generalization of Flipped comes from improved generalization to novel labels.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)
7 Replies