SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.17041 · EMNLP · 2022

GPS: Genetic Prompt Search for Efficient Few-shot Learning

Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Yanggang Wang, Haiyu Li, Zhilin Yang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
hwxu20/gps — 2 of 6
FunctionStatusWhere it lives
augment_prompt Ran hwxu20/gps/ga_processer_t0.py
code served (permissive licence) · get_code("cbf6db8c3c705cb2")
read_task_template Ran hwxu20/gps/ga_processer_t0.py
code served (permissive licence) · get_code("e3b4b752ebd7fb73")
_dump_template Not yet run hwxu20/gps/ga_processer_t0.py
code served (permissive licence) · get_code("db61c525851ad1e1")
check_configs Not yet run hwxu20/gps/ga_processer_t0.py
code served (permissive licence) · get_code("f6de4aa5f12368f0")
ga_process Not yet run hwxu20/gps/ga_processer_t0.py
code served (permissive licence) · get_code("ad8edaebcd28713e")
run_test Not yet run hwxu20/gps/ga_processer_t0.py
code served (permissive licence) · get_code("9ef8c9c9ac454d25")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models. However, their performance heavily relies on the manual design of prompts and thus requires a lot of human efforts. In this paper, we introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts, which utilizes a genetic algorithm to automatically search for high-performing prompts. GPS is gradient-free and requires no update of model parameters but only a small validation set. Experiments on diverse datasets proved the effectiveness of GPS, which outperforms manual prompts by a large margin of 2.6 points. Our method is also better than other parameter-efficient tuning methods such as prompt tuning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.17041")
get_code_for_paper("2210.17041")
have("2210.17041")

Connect an agent — have() is free.