CLLGApr 7, 2023

Revisiting Automated Prompting: Are We Actually Doing Better?

DeepMind
arXiv:2304.03609v2225 citationsh-index: 64
Originality Synthesis-oriented
AI Analysis

This work highlights the need to use manual prompts as a baseline in automated prompting research, addressing a methodological gap for researchers in NLP and AI.

The paper revisits automated prompting techniques across six downstream tasks and various few-shot settings, finding that automated prompting does not consistently outperform simple manual prompts.

Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An attempt to automate human-led prompting followed, with some progress achieved. In particular, subsequent work demonstrates automation can outperform fine-tuning in certain K-shot learning scenarios. In this paper, we revisit techniques for automated prompting on six different downstream tasks and a larger range of K-shot learning settings. We find that automated prompting does not consistently outperform simple manual prompts. Our work suggests that, in addition to fine-tuning, manual prompts should be used as a baseline in this line of research.

Code Implementations1 repo
Foundations

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

Your Notes