Back to Details

literature-review

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Literature Review Writing

文献综述撰写

Synthesize multiple academic papers into a cohesive literature review with thematic organization, trend identification, gap analysis, and proper citation weaving.
将多篇学术论文整合为一篇结构清晰、主题明确的文献综述，涵盖主题梳理、趋势识别、差距分析以及合理的引用融合。

When to Use

适用场景

  • Writing the Introduction or Background section of a manuscript or grant
  • Creating a standalone literature review paper
  • Synthesizing findings from an opencite search session
  • Identifying gaps in the literature to justify new research
  • Preparing a systematic or scoping review
  • 撰写手稿或基金申请的引言/背景部分
  • 创建独立的文献综述论文
  • 整合opencite搜索得到的研究结果
  • 识别文献中的研究空白，为新研究提供依据
  • 准备系统综述或范围综述

Review Types

综述类型

TypePurposeMethodOutput
NarrativeSummarize and interpret a body of literatureSelective, thematicFlowing prose with arguments
SystematicExhaustive, reproducible search with defined criteriaPRISMA protocol, inclusion/exclusionStructured report with methodology
ScopingMap the extent of literature on a topicBroad search, categorizationOverview of themes and gaps
Mini-reviewFocused review for a specific questionTargeted searchBrief, focused synthesis
类型目的方法产出
叙述性综述（Narrative）总结并解读相关文献体系选择性、主题式梳理具有论证逻辑的流畅散文
系统综述（Systematic）基于明确标准进行全面、可复现的文献检索PRISMA协议、纳入/排除标准包含方法论的结构化报告
范围综述（Scoping）梳理某一主题的文献覆盖范围广泛检索、分类整理主题与研究空白的概述
迷你综述（Mini-review）针对特定问题的聚焦式综述定向检索简洁、聚焦的内容整合

Review Pipeline

综述撰写流程

Step 1: Gather Papers

步骤1：收集文献

Use the 
opencite
skill to find relevant literature:
bash
undefined
使用
opencite
Skill查找相关文献：
bash
undefined

Foundational papers

基础文献

uvx opencite canonical "topic" --max 15
uvx opencite canonical "topic" --max 15

Recent work

最新研究

uvx opencite search "specific query" --max 30 --sort date
uvx opencite search "specific query" --max 30 --sort date

Citation network

引用网络

uvx opencite cite "key-paper-DOI" --direction both
uvx opencite cite "key-paper-DOI" --direction both

Download and convert for reading

下载并转换以便阅读

uvx opencite batch-fetch --from-json results.json --convert -o ./papers --summary report.json
undefined
uvx opencite batch-fetch --from-json results.json --convert -o ./papers --summary report.json
undefined

Step 2: Read and Annotate

步骤2：阅读与标注

For each paper, extract:
  • Key finding (1-2 sentences)
  • Method (approach/technique used)
  • Population/context (who/what was studied)
  • Limitations noted by authors
  • How it connects to other papers in the set
Create a synthesis matrix:
PaperFindingMethodSupportsContradicts
Smith 2024X increases YRCT, N=200Jones 2023Lee 2022
Jones 2023X correlates with YSurvey, N=1000Smith 2024--
Lee 2022No effect of X on YMeta-analysis--Smith 2024, Jones 2023
针对每篇论文，提取以下内容：
  • 核心发现（1-2句话）
  • 研究方法（使用的方法/技术）
  • 研究群体/场景（研究对象/背景）
  • 作者指出的局限性
  • 与其他论文的关联
创建整合矩阵：
论文发现方法支持的研究矛盾的研究
Smith 2024X提升YRCT，样本量200Jones 2023Lee 2022
Jones 2023X与Y相关调查，样本量1000Smith 2024--
Lee 2022X对Y无影响元分析--Smith 2024, Jones 2023

Step 3: Identify Themes

步骤3：识别主题

Group papers by theme, not chronologically. Common organizing structures:
  • By methodology: group studies using similar approaches
  • By finding: group studies with converging/diverging results
  • By population: group by subject type or context
  • By theoretical framework: group by underlying model
  • Chronological evolution: trace how understanding changed over time (use sparingly)
按主题而非时间顺序对论文分组。常见的组织结构：
  • 按研究方法：将使用相似方法的研究分组
  • 按研究发现：将结论一致或相悖的研究分组
  • 按研究群体：按研究对象类型或场景分组
  • 按理论框架：按背后的模型分组
  • 时间演化：追踪认知随时间的变化（谨慎使用）

Step 4: Write the Review

步骤4：撰写综述

Structure Per Section/Paragraph

段落/章节结构

Each paragraph in a literature review should:
  1. Topic sentence: State the theme or claim this paragraph addresses
  2. Evidence: Cite 2-5 papers supporting or nuancing this claim
  3. Synthesis: Compare, contrast, and connect the cited works
  4. Transition: Lead to the next theme or the gap
文献综述的每个段落应包含：
  1. 主题句：说明本段要阐述的主题或观点
  2. 证据：引用2-5篇支持或细化该观点的论文
  3. 整合分析：对比、关联引用的研究
  4. 过渡句：引出下一个主题或研究空白

Citation Weaving Patterns

引用融合模式

Integral citation (author as subject): "Smith et al. (2024) demonstrated that X increases Y using a randomized controlled trial with 200 participants."
Non-integral citation (finding as subject): "Recent evidence suggests that X increases Y in controlled settings (Smith et al., 2024; Jones et al., 2023), although this effect may be population-dependent (Lee et al., 2022)."
Synthesis citation (multiple sources for one claim): "Several studies have converged on the finding that X modulates Y through mechanism Z (Smith et al., 2024; Jones et al., 2023; Chen et al., 2021), with effect sizes ranging from d = 0.3 to d = 0.8."
Contrast citation: "While Smith et al. (2024) found significant effects using direct measurement, Lee et al. (2022) reported null results in a meta-analysis of self-report studies, suggesting that measurement approach may moderate the effect."
整合式引用（作者作为主语）： "Smith等人（2024）通过包含200名参与者的随机对照试验（RCT）证明X提升了Y。"
非整合式引用（研究发现作为主语）： "近期证据表明，在受控场景中X可提升Y（Smith等人，2024；Jones等人，2023），不过该效果可能受群体差异影响（Lee等人，2022）。"
整合式多源引用（多个来源支撑同一观点）： "多项研究一致发现X通过机制Z调节Y（Smith等人，2024；Jones等人，2023；Chen等人，2021），效应量范围为d=0.3至d=0.8。"
对比式引用： "Smith等人（2024）通过直接测量发现显著效应，而Lee等人（2022）在一项自我报告研究的元分析中报告无显著结果，这表明测量方法可能会调节效应。"

Avoid Common Pitfalls

避免常见误区

  • Annotated bibliography: Don't just summarize each paper sequentially. Synthesize.
  • String-of-pearls: Don't write "Smith found X. Jones found Y. Lee found Z." Connect them.
  • Overclaiming: Don't say "proves" or "definitively shows." Use "suggests," "indicates," "provides evidence for."
  • Recency bias: Include foundational/seminal work, not just the last 2 years.
  • Confirmation bias: Include contradictory findings and explain discrepancies.
  • 注释性书目：不要按顺序逐一总结每篇论文，要进行整合分析。
  • 珍珠串式罗列：不要写“Smith发现X。Jones发现Y。Lee发现Z。”要建立它们之间的关联。
  • 过度断言：不要使用“证明”或“明确表明”，使用“表明”“显示”“为……提供证据”。
  • 近期偏差：要纳入基础/开创性研究，而不仅仅是过去2年的成果。
  • 确认偏差：要纳入相悖的发现并解释差异。

Step 5: Identify the Gap

步骤5：识别研究空白

After synthesizing existing literature, articulate what is missing:
Gap statement patterns:
  • "Despite these advances, no study has examined {specific question}."
  • "While X has been established for {context A}, it remains unclear whether this extends to {context B}."
  • "Existing studies are limited by {methodological issue}, and {new approach} could address this."
  • "The relationship between X and Y has been studied in isolation, but their interaction under {condition} is unexplored."
在整合现有文献后，明确指出缺失的内容：
研究空白表述模式：
  • “尽管取得了这些进展，但尚无研究探讨{具体问题}。”
  • “虽然X在{场景A}中已得到证实，但尚不清楚这是否适用于{场景B}。”
  • “现有研究受限于{方法论问题}，而{新方法}可解决这一问题。”
  • “X与Y的关系已被单独研究，但它们在{条件}下的相互作用尚未被探索。”

Step 6: Generate Bibliography

步骤6：生成参考文献

bash
undefined
bash
undefined

Export BibTeX for all cited papers

导出所有引用论文的BibTeX格式

for doi in $(cat cited_dois.txt); do uvx opencite lookup "$doi" -f bibtex --append-bib review_refs.bib done
undefined
for doi in $(cat cited_dois.txt); do uvx opencite lookup "$doi" -f bibtex --append-bib review_refs.bib done
undefined

Output Format

产出格式

markdown
undefined
markdown
undefined

Literature Review: {Topic}

文献综述：{主题}

{Theme 1 Title}

{主题1标题}

{Synthesized paragraphs with citations}
{包含引用的整合段落}

{Theme 2 Title}

{主题2标题}

{Synthesized paragraphs with citations}
{包含引用的整合段落}

{Theme 3 Title}

{主题3标题}

{Synthesized paragraphs with citations}
{包含引用的整合段落}

Current Gaps and Future Directions

当前研究空白与未来方向

{Gap analysis and research opportunities}
{差距分析与研究机会}

References

参考文献

{BibTeX file or formatted reference list}
undefined
{BibTeX文件或格式化参考文献列表}
undefined

Quality Checklist

质量检查清单

  • Organized thematically (not paper-by-paper)
  • Each paragraph synthesizes multiple sources
  • Citations woven into prose (not parenthetical dumps)
  • Contradictory findings acknowledged and explained
  • Seminal/foundational work included
  • Recent work (last 2-3 years) included
  • Gap statement clearly articulated
  • Transition sentences connect paragraphs and sections
  • No overclaiming (appropriate hedging)
  • All cited papers in reference list
  • 按主题组织（而非按论文逐一罗列）
  • 每个段落整合了多个来源
  • 引用融入正文（而非堆砌括号标注）
  • 认可并解释了相悖的研究发现
  • 纳入了开创性/基础研究
  • 纳入了近期研究（过去2-3年）
  • 明确表述了研究空白
  • 过渡句连接了段落和章节
  • 无过度断言（使用恰当的模糊表述）
  • 所有引用的论文均在参考文献列表中

Additional Resources

额外资源

  • Reference: references/review-frameworks.md - PRISMA, PICO, and other review frameworks
  • 参考资料：references/review-frameworks.md - PRISMA、PICO及其他综述框架