Saved in:
Bibliographic Details
Main Authors: Passigan, Pascal, Yohannes, Kidus, Pereira, Joshua
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.10323
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • The wayward quality of continuous prompts stresses the importance of their interpretability as unexpected and unpredictable behaviors appear following training, especially in the context of large language models automating people-sensitive tasks such as resume screening. In this paper we present a novel method of constructing continuous prompts via discrete prompt embeddings and evaluate improvements to continuous prompt interpretability and inference accuracy. For a set of manually designed discrete prompts $\mathcal{D}$, which we tokenize and embed each into tensor form, we train a model to predict the weights such that the linear combinations of those prompts correspond to higher performance on natural language understanding tasks.