Anthropic 定量测试 Claude 长上下文提示词技巧
Anthropic 发布实验数据：提取相关引用加示例，能提升 Claude 长文档召回准确率，提示词工程有实证方法。
Claude 的上下文窗口（单次能处理的文本量）已达 10 万 token，可读完一整本书。Anthropic 用政府文件做了定量实验：先提取与问题相关的原文引用，再补充其他章节的正确问答示例，这两种提示词方法都能显著提升 Claude 在长文档中回忆信息的准确率。
正文摘录
Product Prompt engineering for Claude's long context window Sep 23, 2023  Claude’s [100,000 token long context window](https://www.anthropic.com/news/100k-context-windows) enables the model to operate over hundreds of pages of technical documentation, or even an [entire book](https://twitter.com/AnthropicAI/status/1656700156518060033). As we continue to scale the Claude API, we’re seeing increased demand for prompting guidance on how to maximize Claude’s potential. Today, we’re pleased to share a quantitative case study on two techniques that can improve Claude’s recall over long contexts: - Extracting reference quotes relevant to the question before answering - Supplementing the prompt with examples of corre…