CLLGMar 18, 2021

GPT Understands, Too

arXiv:2103.10385v21433 citations
AI Analysis

This addresses the problem of prompt sensitivity for researchers and practitioners in natural language understanding, offering a more stable and effective method.

The paper tackles the instability of manual discrete prompts in language models by introducing P-Tuning, which uses trainable continuous prompt embeddings, resulting in improved performance on NLU tasks like LAMA and SuperGLUE.

Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU). However, our preliminary study reveals that manual discrete prompts often lead to unstable performance -- e.g., changing a single word in the prompt might result in substantial performance drop. We propose a novel method P-Tuning that employs trainable continuous prompt embeddings in concatenation with discrete prompts. Empirically, P-Tuning not only stabilizes training by minimizing the gap between various discrete prompts, but also improves performance by a sizeable margin on a wide range of NLU tasks including LAMA and SuperGLUE. P-Tuning is generally effective for both frozen and tuned language models, under both the fully-supervised and few-shot settings.

Code Implementations10 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes