优化提示词中的输入数据，让大模型表现更佳。
ADO: Automatic Data Optimization for Inputs in LLM Prompts
- 通过补全缺失信息、删无关属性、生成推断内容来改进输入
- 对输入结构重新排布，提升大模型对格式的适应性
- 适合想提升提示工程效果的研究者和开发者
本研究探索通过优化提示词中的输入数据来提升大语言模型（LLM）性能的新方法。以往研究多聚焦于指令优化和引入上下文示例，而本文关注输入数据本身的优化潜力。提出双路径策略：内容工程（补全缺失值、移除无关属性、基于已有属性生成补充信息）与结构重构（优化修改后内容的呈现方式，以适配大模型对输入格式的敏感性）。实验表明，该优化可显著提升大模型在多种任务中的表现，为提示工程提供新方向。代码已公开于 https://anonymous.4open.science/r/ADO-6BC5/
原文摘要 · Abstract (English)
This study explores a novel approach to enhance the performance of Large Language Models (LLMs) through the optimization of input data within prompts. While previous research has primarily focused on refining instruction components and augmenting input data with in-context examples, our work investigates the potential benefits of optimizing the input data itself. We introduce a two-pronged strategy for input data optimization: content engineering and structural reformulation. Content engineering involves imputing missing values, removing irrelevant attributes, and enriching profiles by generating additional information inferred from existing attributes. Subsequent to content engineering, structural reformulation is applied to optimize the presentation of the modified content to LLMs, given their sensitivity to input format. Our findings suggest that these optimizations can significantly improve the performance of LLMs in various tasks, offering a promising avenue for future research in prompt engineering. The source code is available at https://anonymous.4open.science/r/ADO-6BC5/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。