On Conditional and Compositional Language Model Differentiable Prompting

TL;DR

This paper introduces PRopS, a modular neural model for transforming task instructions into prompts, enhancing language model adaptation with superior compositional generalization, few-shot learning, and fewer parameters.

Contribution

The paper proposes PRopS, a neural production system-based prompt generator that learns discrete transformation rules, improving PLM adaptation for various tasks over existing methods.

Findings

PRopS outperforms other PLM adaptation techniques on multiple tasks.

PRopS often surpasses fully fine-tuned models in performance.

PRopS requires fewer trainable parameters than traditional fine-tuning.

Abstract

Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. Prompts can be represented by a human-engineered word sequence or by a learned continuous embedding. In this work, we investigate conditional and compositional differentiable prompting. We propose a new model, Prompt Production System (PRopS), which learns to transform task instructions or input metadata, into continuous prompts that elicit task-specific outputs from the PLM. Our model uses a modular network structure based on our neural formulation of Production Systems, which allows the model to learn discrete rules -- neural functions that learn to specialize in transforming particular prompt input patterns, making it suitable for compositional transfer learning and few-shot learning. We present extensive empirical and theoretical analysis and show that PRopS consistently surpasses other PLM adaptation techniques, and often improves upon fully fine-tuned models, on compositional generalization tasks, controllable summarization and multilingual translation, while needing fewer trainable parameters.