PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 19, 20240 citationsOpen Access

Dual-Phase Accelerated Prompt Optimization

View Full Paper
MYMuchen YangMLMoxin LiYLYongle Li

Key Points

Key points are not available for this paper at this time.

Abstract

Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of high-quality prompt initialization and the identification of effective optimization directions, thus resulting in substantial optimization steps to obtain satisfactory performance. In this light, we aim to accelerate prompt optimization process to tackle the challenge of low convergence rate. We propose a dual-phase approach which starts with generating high-quality initial prompts by adopting a well-designed meta-instruction to delve into task-specific information, and iteratively optimize the prompts at the sentence level, leveraging previous tuning experience to expand prompt candidates and accept effective ones. Extensive experiments on eight datasets demonstrate the effectiveness of our proposed method, achieving a consistent accuracy gain over baselines with less than five optimization steps.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Yang et al. (2024) studied this question.

synapsesocial.com/papers/68e642a2b6db6435875d45f1https://doi.org/10.48550/arxiv.2406.13443
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization2024 · 1 citations
  2. 2Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers2024
  3. 3DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective2025
  4. 4Localized Zeroth-Order Prompt Optimization2024 · 1 citations
  5. 5Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation2025