跳到主要内容Skip to main content
← 深水指南Guides

文献筛选Literature screening

提示词与工作流Prompts & workflows · 提示词案例Prompt case

输出筛选表与理由;只依据标题摘要,不编全文结论。

Output a screening table with reasons; use titles/abstracts only and do not invent full-text conclusions.

提示词效果未实测。Prompt effect has not been tested.

提示词是可复跑的模板,不是效果承诺。换模型、换版本、换输入都可能改变结果;用本页的检查点自己核对,并把官方出处当作机制依据而不是效果保证。A prompt is a re-runnable template, not a promise of results. Changing the model, version or input can change the outcome. Use the checkpoints on this page to verify it yourself, and treat the official sources as evidence of mechanism rather than a guarantee of effect.

任务与输入Task and inputs

按纳入排除标准筛选文献。 输入:文献标题摘要、纳入标准、排除标准。

Output a screening table with reasons; use titles/abstracts only and do not invent full-text conclusions. Inputs: Titles/abstracts, inclusion criteria, and exclusion criteria.

提示词本体The prompt

按标准筛选文献。输出 decisions[]:id、decision(include/exclude/uncertain)、criterion、quote。quote 来自标题/摘要;uncertain 必须写缺什么信息。不得依据未提供的全文下结论。

占位符用 {字段} 标注,运行前替换为本次输入。

Screen literature by criteria. Output decisions[] with id, decision (include/exclude/uncertain), criterion and quote. quote comes from title/abstract; uncertain must state missing information. Do not conclude from full text that was not provided.

Replace {field} placeholders with the current inputs before running.

预期输出形态Expected output shape

decisions[],含标准与逐字依据。

decisions[] with criteria and verbatim basis.

检查点Checkpoints

  • 每条 decision 有 criterion。
  • quote 在摘要/标题中。
  • uncertain 写缺失信息。
  • Each decision has a criterion.
  • Quotes appear in title/abstract.
  • Uncertain items state missing information.

失败分支Failure branches

  • 标准模糊:先写可判定条件。
  • 摘要不够:标 uncertain 待全文。
  • Vague criteria: write decidable conditions first.
  • Abstract insufficient: mark uncertain pending full text.

出处与边界Sources and limits

提示词效果未实测。机制依据见出处;换模型、版本或输入会改变结果。

This site has not tested the effect of this prompt. See the sources for the mechanism; changing model, version or input can change the result.

出处Sources

来源Source链接URL
OpenAI Cookbook · Building resilient prompts using an evaluation flywheel(官方仓库 raw,2026-11-07 直抓 200)OpenAI Cookbook: Building resilient prompts using an evaluation flywheel (official repository raw, fetched 200 on 2026-11-07)https://raw.githubusercontent.com/openai/openai-cookbook/main/examples/evaluation/Building_resilient_prompts_using_an_evaluation_flywheel.mdhttps://raw.githubusercontent.com/openai/openai-cookbook/main/examples/evaluation/Building_resilient_prompts_using_an_evaluation_flywheel.md

资料快照日期:2026-11-07;单项复核范围与日期见对应正文或来源记录。产品功能与条款可能变化,使用前请核对原始来源。Source snapshot: 2026-11-07; item-specific rechecks and their scope are recorded in the text or source notes. Features and terms may change; check the original sources before use.