文献矩阵是好文献综述背后的工作台。下面 15 个 Prompt 帮你设计列、从摘要填行、审计空白、把矩阵转成段落。可用于 Notion、Excel、Airtable，或你已经在用的任何工具。
适合哪些场景
管理 30-100+ 篇文献的论文作者、系统评价小组、整理大纲的助教，以及在写综述章节或基金申请的研究者。
什么时候不建议这样写 Prompt
少于 10 篇时不用矩阵——一般文献清单足够。摘要都没读过也不要做——AI 编出来的行比没行更糟。
Prompt 结构公式
矩阵 Prompt 一定要带这六个要素：
- 角色：AI 扮演谁——研究导师、同行评议人、考试教练、辩论对手、图书馆员。
- 上下文：水平、学科、deadline、论文数量、引用风格、课程或项目。
- 目标：一个具体交付物——12 道题、1 页文献矩阵、5 条反论、4 周复习计划。
- 限制：字数、深度、允许的来源类型、跳过什么、绝不主张什么。
- 输出格式：编号清单、表格、JSON 或分级块（E / M / H），能粘到 Notion / Anki / Word。
- 示例 / 信号：1-2 段参考或反例（“不要像维基那样讲”）。
这套 Prompt 适合用在哪
- 论文文献综述章节
- 系统评价证据抽取
- 基金申请相关工作段
- 课程大纲设计
- 私人研究 dashboard
15 个可直接复制的 Prompt 模板
1. 列设计 Prompt
先做这步，烂列害死整张矩阵。
You are a research methods coach. I am building a literature matrix on {topic} in {field}. Suggest 10 columns I should include, ordered by importance. For each: column name, what it captures, a sample value, and whether it is mandatory or optional.可替换变量： topic, field
优化建议： 列太空泛时追加：“Tailor columns to my specific research question: {paste question}. Drop columns irrelevant to that question.”
2. 从摘要填一行
Below is an abstract. Fill in the matrix row using these columns: {Citation | Question | Design | N | Sample | Key DV | Finding | Effect size | Limitations | Relevance to my project}. Use "not reported" if not stated. Cite from the abstract; do not infer.
{paste abstract}3. 批量填行（5 篇）
Below are 5 abstracts. For each, produce one row of my matrix with these columns: {paste column headers}. Output as a markdown table with one row per paper. Use "not reported" when needed.
{paste abstracts}4. 方法学侧重矩阵
Build a methods-focused matrix on {topic}: columns = {Citation | Design | Sampling | Measures | Analysis | Strengths | Weaknesses}. From these papers: {paste citations + key methods sections}.5. 发现侧重矩阵
Build a findings-focused matrix on {topic}: columns = {Citation | Primary finding | Effect size | Replicated? | Boundary condition | Counter-evidence}. From these papers: {paste results}.6. 理论框架列
For these {N} papers, identify which theoretical frame each uses (or "atheoretical"). Output a 2-column list: citation | theoretical frame. Group at the end by frame to show clustering.
{paste citations + abstracts}7. 空白检测查询
Below is my partially-populated matrix. Identify 3 gaps: which combinations of columns are underrepresented (e.g., a population x method cell with few rows), and suggest 2-3 papers I should look for to fill each gap.
{paste matrix}8. 行聚类
Below is my matrix with {N} rows. Cluster the rows into 3-5 groups based on shared characteristics (method, theory, population, finding). Name each cluster and list the citations belonging to it. Note 1-2 outliers.
{paste matrix}9. 质量评分列
For each row in my matrix, add a quality-rating column (1-5) based on: study design, sample size, generalizability, reporting transparency. Output the rating, the 1-sentence justification, and any flags (high-risk-of-bias, conflict-of-interest).
{paste matrix}10. 矩阵 → 综合段
Convert my matrix into a 250-word synthesis paragraph for a thesis chapter: what the literature has established, where findings converge, where they diverge, and what remains unclear. Cite at least 5 papers by first author + year.
{paste matrix}11. PRISMA 体筛查
Below are 20 abstracts. Apply my inclusion criteria {paste criteria} and exclusion criteria {paste criteria}. Output 4 categories: include, exclude (reason), unclear-needs-full-text, off-topic.
{paste abstracts}12. 引用密度检查
Below is my matrix. For each row, indicate how often this paper is cited in the others (via author + year mentions). Identify the most-cited "hub" papers and the more isolated ones.
{paste matrix with abstracts or excerpts}13. 矩阵更新工作流
I added 5 new papers to my matrix. Help me update: (a) check whether any of my existing rows need revision based on the new ones, (b) flag if the new findings contradict prior clusters, (c) suggest 1-line additions to the synthesis paragraph.
Old matrix: {paste}
New rows: {paste}14. Notion 列规范
Convert my matrix into Notion-friendly column schema with: property name, property type (text / select / multi-select / number / date / relation), description, sample value. Output as a list ready to paste into a Notion database creation flow.
{paste matrix columns}15. 评议人答辩简报
My lit matrix supports the thesis "{thesis}". Generate a 150-word defense paragraph: how the matrix shows the thesis is grounded, which key papers anchor each claim, and how I would respond if a reviewer said the lit review is too narrow.容易踩的坑
- 没确定研究问题就设计列——列要服务问题。
- 让 AI 不看正文就填行——编出的行比缺行更糟。
- 列太多——8-12 列是甜点。
- 没有”与我项目的相关度”列——矩阵会变成通用数据库。
- 把矩阵当静态——每读一节都更新。
- 不写综合段（模板 10）——矩阵是输入不是输出。
- 不评质量（模板 9）——不是每行权重相同。
优化技巧
- 先选平台（Notion / Excel / Airtable / Zotero）——中途换平台很痛。
- 先做 5 篇 pilot，再按收获扩列。
- 系统评价按 PRISMA 做筛查（模板 11）。
- 永远留一个”notes”列放结构化列装不下的想法。
- 每加 25 行重新聚类一次——数据多了聚类会变。
- 写综述章节前先把矩阵转成综合段（模板 10）。
- 建一个”被剔除”子表 + 原因，答辩时方便守 scope。
FAQ
- 一个矩阵多少篇合适？: 本科荣誉论文 20-40；硕士 40-80；博士章节 80-200；系统评价由筛查决定。
- AI 能填整张矩阵吗？: 不能——但你粘真实摘要时它能稳定填行。每 10 行抽 1 行核对原文。
- 最重要的一列是？: “与我项目的相关度”——没有它，矩阵只是通用数据库。
- Notion 还是 Excel？: 协作和数据库关联用 Notion；独立做系统评价或导给文献管理器用 Excel。
- 怎么避免矩阵变陈旧？: 每周留 30 分钟读 3-5 篇新文献并更新——把它当活文档而不是一次性任务。