Yarin Gal, Ilia Shumailov, Yiren Zhao, Robert Mullins, Yulin Zhou
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 that automation can outperform fine-tuning in certain K-shot learning scenarios (Shin et al., 2020;Zhang et al., 2021). 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 prompting. Our work suggests that, in addition to fine-tuning, manual prompting should be used as a baseline in this line of research.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.03609")
get_code_for_paper("2304.03609")
have("2304.03609")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2304.03609.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2304.03609)
Connect an agent — have() is free.