GRIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023(2023)
摘要
Providing natural language instructions in prompts is a useful new paradigm for improving task performance of large language models in a zero-shot setting. Recent work has aimed to improve such prompts via manual rewriting or gradient-based tuning. However, manual rewriting is time-consuming and requires subjective interpretation, while gradient-based tuning can be extremely computationally demanding for large models and may not be feasible for API-based models. In this work, we introduce Gradient-free Instructional Prompt Search (GRIPS), a gradient-free, edit-based search approach for improving task instructions for large language models. GRIPS takes in instructions designed for humans and automatically returns an improved, edited prompt, while allowing for API-based tuning. With InstructGPT models, GRIPS improves the average task performance by up to 4.30 percentage points on eight classification tasks from the NATURAL-INSTRUCTIONS dataset (with similar improvements for OPT, BLOOM, and FLANT5). We see improvements for both instructiononly prompts and instruction + k-shot examples prompts. Notably, GRIPS outperforms manual rewriting and purely example-based prompts while controlling for the available compute and data budget. Further, performance of GRIPS is comparable to select gradient-based tuning approaches. Qualitatively, we show our edits can simplify instructions and at times make them incoherent but nonetheless improve accuracy.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要