English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large language models (LLMs) have shown increasing power on various naturallanguage processing (NLP) tasks. However, tuning these models for downstreamtasks usually needs exorbitant costs or is unavailable due to commercialconsiderations. Recently, black-box tuning has been proposed to address thisproblem by optimizing task-specific prompts without accessing the gradients andhidden representations. However, most existing works have yet fully exploitedthe potential of gradient-free optimization under the scenario of few-shotlearning. In this paper, we describe BBT-RGB, a suite of straightforward andcomplementary techniques for enhancing the efficiency and performance ofblack-box optimization. Specifically, our method includes three plug-and-playcomponents: (1) Two-stage derivative-free optimization strategy thatfacilitates fast convergence and mitigates overfitting; (2) Automaticverbalizer construction with its novel usage under few-shot settings; (3)Better prompt initialization policy based on instruction search andauto-selected demonstration. Extensive experiments across various tasks onnatural language understanding and inference demonstrate the effectiveness ofour method. Our codes are publicly available athttps://github.com/QiushiSun/BBT-RGB.

Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives