Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 3, 2024Open Access

Automatic Prompt Selection for Large Language Models

View Full Paper
Ask AI
Bookmark
Share

Authors

VDViet-Tung DoVHVan-Khanh HoangDNDuy‐Hung Nguyen

Discussion

Loading...

Member takes

Overview

Proposed approach selects optimal prompts for inputs in large language models, suggesting improved efficiency in prompt design.

Key Points

  • The proposed method selects the best prompt, improving efficiency and effectiveness when using large language models.
  • It achieves competitive performance on zero-shot question-answering datasets like GSM8K and AQuA, showcasing its utility.
  • A method involving clustering, prompt generation, and ranking enhances prompt optimization compared to existing models based on manual design alone. This framework effectively streamlines the prompt selection process, reducing time and resource demands.

Cite This Study

Do et al. (2024) studied this question.

synapsesocial.com/papers/68e708e7b6db643587683036https://doi.org/10.48550/arxiv.2404.02717
View Full Paper
Ask AI
Bookmark
Share

Also Consider

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

  1. 1Efficient Prompting Methods for Large Language Models: A Survey2024 · 18 citations
  2. 2S2LPP: Small-to-Large Prompt Prediction across LLMs2025
  3. 3RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents2024 · 1 citations
  4. 4MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization2024 · 2 citations
  5. 5PhaseEvo: Towards Unified In-Context Prompt Optimization for Large Language Models2024 · 1 citations