Prompt Waywardness The Curious Case of Discretized Interpretation of Continuous Prompts
>> YOUR LINK HERE: ___ http://youtube.com/watch?v=EfGaSciDN9Y
Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning. Motivated by these promising results, we investigate the feasibility of extracting a discrete (textual) interpretation of continuous prompts that is faithful to the problem they solve. In practice, we observe a wayward behavior between the task solved by continuous prompts and their nearest neighbor discrete projections: We can find continuous prompts that solve a task while being projected to an arbitrary text (e.g., definition of a different or even a contradictory task), while being within a very small (2%) margin of the best continuous prompt of the same size for the task. • • Details in paper: https://arxiv.org/abs/2112.08348
#############################
