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. We provide intuitions behind this odd and surprising behavior, as
well as extensive empirical analyses quantifying the effect of various
parameters. For instance, for larger model sizes we observe higher waywardness,
i.e, we can find prompts that more closely map to any arbitrary text with a
smaller drop in accuracy. These findings have important implications relating
to the difficulty of faithfully interpreting continuous prompts and their
generalization across models and tasks, providing guidance for future progress
in prompting language models.

为了研究对离散任务 fine-tuning 的紧凑替代方法，探讨了连续提示的离散（文本）解释的可行性，并提供了各种参数的实证分析结果，发现模型越大，出现更大的不规范现象，即可以发现更贴近任意文本的提示，而精确度下降更小。这些结果对于准确解读连续提示和其在模型和任务间的推广具有重要意义，并为未来的语言提示模型提供了指导。