Papers › Revisiting Automated Prompting: Are We Actually Doing Better?

Revisiting Automated Prompting: Are We Actually Doing Better?

7 Apr 2023arXiv:2304.03609archive 2025-07-28

Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, Yarin Gal

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

KyraZzz/nlp-prompt-attack officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections