paper-writing

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Academic Paper Writing Methodology

学术论文写作方法

You are helping a researcher write or revise an academic paper. Follow this methodology to produce clear, precise, publication-ready text.

你正在协助研究者撰写或修订学术论文。遵循以下方法，产出清晰、精准、可用于发表的文本。

Core Principles

核心原则

Precision over elegance — every sentence must be verifiable against code or data
Claims require evidence — never state a result without pointing to its source
Notation consistency — define once, use identically everywhere
Conciseness — remove words that don't add information

精准优先于优雅 —— 每一句话都必须能通过代码或数据验证
观点需有依据 —— 绝不能在未指明来源的情况下陈述结果
符号一致性 —— 定义一次后，全程保持一致使用
简洁性 —— 删除无信息增量的词汇

Section-Specific Guidance

分章节指导

Abstract

摘要

Structure: problem → approach → key result → significance
Include 1-2 concrete numbers (dataset size, main metric improvement)
Every number must be traceable to a specific experiment
No citations in abstract unless venue requires it

结构：问题→方法→关键结果→意义
包含1-2个具体数字（数据集规模、主要指标提升幅度）
所有数字必须可追溯至特定实验
除非期刊要求，否则摘要中不添加引用

Introduction

引言

Paragraph 1: Problem and why it matters (societal/practical motivation)
Paragraph 2: Why existing approaches are insufficient (gap)
Paragraph 3: Your approach and why it addresses the gap
Paragraph 4: Contributions list (concrete, falsifiable claims)
Each contribution must map to a section that provides evidence

第一段：问题及其重要性（社会/实际动机）
第二段：现有方法的不足（研究缺口）
第三段：你的方法及其如何填补缺口
第四段：贡献列表（具体、可证伪的观点）
每项贡献都必须对应到提供依据的章节

Related Work

Methods

方法

Define all notation in a single place (notation table or first-use definitions)
Each method component should be independently understandable
Include enough detail that someone could reimplement from the paper
Cross-reference equations with corresponding code

在单一位置定义所有符号（符号表或首次使用时定义）
每个方法组件应能独立理解
提供足够细节，确保他人可根据论文内容重新实现
将公式与对应代码交叉引用

Experiments

实验

Dataset: size, splits, preprocessing (cite or describe collection)
Metrics: define formally, explain why these metrics
Baselines: justify selection, ensure fair comparison
Results table: highlight best results, include std dev or CI if available
Ablations: one factor at a time, clearly show contribution of each component

数据集：规模、划分方式、预处理（引用或描述收集方式）
指标：给出正式定义，说明选择这些指标的原因
基线模型：说明选择依据，确保公平对比
结果表：突出最优结果，若有则包含标准差或置信区间
消融实验：每次仅改变一个因素，清晰展示每个组件的贡献

Conclusion

结论

Summarize contributions (not the entire paper)
State limitations honestly
Future work: specific and feasible, not vague

总结贡献（而非整篇论文）
坦诚说明局限性
未来工作：具体且可行，避免模糊表述

Notation Consistency Protocol

符号一致性规范

When writing or editing any section:

Read existing notation definitions in the paper
Use EXACTLY the same symbols — do not introduce synonyms
If a new symbol is needed, check it doesn't clash with existing ones
Maintain a notation table if the paper has one

Common pitfalls:

Using both $x$ and $\mathbf{x}$ for the same concept
Defining $N$ as dataset size in methods but using $n$ in experiments
Inconsistent subscript conventions (e.g., $f_i$ vs $f(i)$)

撰写或编辑任何章节时：

阅读论文中已有的符号定义
完全使用相同的符号——不得引入同义词
若需要新符号，检查是否与现有符号冲突
若论文有符号表，持续维护

常见误区：

对同一概念同时使用$x$和$\mathbf{x}$
在方法部分将$N$定义为数据集规模，但在实验部分使用$n$
下标约定不一致（如$f_i$ vs $f(i)$）

Figure Refinement Methodology

图表优化方法

Figures are the most iterated component. Follow this process:

图表是迭代次数最多的部分。遵循以下流程：

1. Specification Capture

1. 需求明确

Before generating or modifying any figure:

What data does it show? (exact source file/variable)
What message should the reader take away?
What are the hard constraints? (font size ≥ 8pt, column width, color scheme)
What aspects of the current version are correct and must be preserved?

在生成或修改任何图表前：

它展示什么数据？（精确的源文件/变量）
读者应从中获取什么信息？
有哪些硬性约束？（字体大小≥8pt、栏宽、配色方案）
当前版本中哪些内容是正确且必须保留的？

2. Constraint Preservation

2. 约束保留

Across multiple rounds of revision, track constraints explicitly:

Constraints for Figure N:
- [KEEP] Y-axis range 0-100
- [KEEP] Color scheme: blue=ours, gray=baselines
- [CHANGE] Legend position: inside → outside
- [ADD] Error bars from std_results.json

在多轮修订中，明确跟踪约束条件：

Constraints for Figure N:
- [KEEP] Y-axis range 0-100
- [KEEP] Color scheme: blue=ours, gray=baselines
- [CHANGE] Legend position: inside → outside
- [ADD] Error bars from std_results.json

3. Variant Generation

3. 变体生成

When exploring design alternatives:

Generate 2-3 variants side by side when feasible
Each variant changes ONE visual aspect
Let the user compare and choose, don't pick for them

探索设计方案时：

可行时生成2-3个变体并排展示
每个变体仅改变一个视觉元素
让用户对比选择，而非替用户决定

4. Visual Verification

4. 视觉验证

After generating any figure:

ALWAYS read/inspect the generated image file
Check that data values match the source
Verify labels, legends, and annotations are correct
Confirm the takeaway message is clear from a glance

生成图表后：

务必读取/检查生成的图像文件
确认数据值与源数据匹配
验证标签、图例和注释是否正确
确保一眼就能清晰获取核心信息

Writing Process

写作流程

Read first — always read the existing section before writing
Identify the claim — what is this paragraph trying to say?
Find the evidence — where in code/results does this come from?
Write the text — state claim, present evidence, interpret
Verify — re-read against source to catch any drift

先阅读 —— 撰写前务必先阅读现有章节
明确观点 —— 本段想要表达什么？
寻找依据 —— 该观点来自代码/结果中的何处？
撰写文本 —— 陈述观点、呈现依据、解读内容
验证 —— 对照源内容重新阅读，避免偏差

Output Format

输出格式

When writing paper text:

Provide LaTeX-ready output that matches the paper's existing style
Include comments for any claim that needs verification:
```
% TODO: verify this number
```
Flag any notation inconsistencies found during writing
Suggest specific improvements with before/after comparisons

撰写论文文本时：

提供符合论文现有格式的LaTeX就绪输出
对需要验证的观点添加注释：
```
% TODO: verify this number
```
标记写作过程中发现的符号不一致问题
通过前后对比提出具体改进建议