Skip to content

3.1 Prompt Design and Practical Refinement

What you will learn on this page

  • Core principles of prompt design (5W1H, role assignment, few-shot prompting)
  • Prompt strategies for refining existing English
  • A “fix your claim in Japanese first, then convert to English” approach
  • Step-by-step prompt refinement (iterative improvement)
  • A template library by purpose (style, proofreading, tense checks, logical flow, comprehensive checks)
  • How to compare and evaluate AI outputs
  • When to stop refining (a practical stopping rule)
  • How to leverage saved custom instructions

How this page fits in

On 2.3 Academic Style, Tense, and Logical Flow, we explained rules of academic style, tense conventions, logical flow, and pre-editing for Japanese drafts intended for translation. This page builds on that knowledge and focuses on a practical workflow for designing prompts and refining English step by step.

Core principle: Do not let AI produce the “answer”

Generative AI can be used either as a tool that helps you develop your English or as a tool that replaces your English. A key way to stay on the “development” side is to fix AI’s role as an amplifier of your thinking and expression, rather than asking it to produce the content for you.

Recall the Augmented Competence model introduced in 1.2 Academic Integrity and Plagiarism Prevention. Refinement with AI assumes you stay within your own receptive competence. If you cannot ask yourself “Why is this better?” or “Do I fully understand this expression?”, the process shifts from augmentation to replacement.

It helps to define a minimal personal rule set to reduce mistakes.

Example personal rules

“Structure consultation, example phrases, paraphrase suggestions, grammar explanations, and checking are OK. Fabricating content, generating citations without evidence, and producing a full submission as-is are not allowed.”

Principles of prompt design

The basics

Output quality changes dramatically depending on the prompt. When people feel that “AI is not useful for academic writing,” the prompt is often vague, or the user stops after one attempt.

Three principles:

  1. Provide more detailed context: Instead of “Fix this,” specify criteria, perspective, and constraints.
  2. Give clear and precise instructions: AI follows instructions literally, so reduce ambiguity.
  3. Iterate: Outputs vary. Keep the conversation going by stating what you dislike and what you want improved.

Yanase (2023) also notes two key cautions for style improvement with ChatGPT.

Caution 1: Give objective, explicit instructions
Treat prompting like programming. State the goal, audience, context, and constraints explicitly. Even for translation, specifying the purpose and target audience improves output quality (Yamada, 2023).

Caution 2: Do not assume human-like understanding
Better prompts improve responses, but AI does not “understand meaning” like humans. If you write “Improve the flow,” it may emphasize aspects you did not intend. Make instructions more concrete, for example by adding “The core of the argument is …” or “by emphasizing …”.

Practical techniques

  1. Assign a role: e.g., “You are an expert academic editor.”
  2. Use delimiters and structure markers: # for sections, <<< >>> for quoted input, etc.
  3. Use few-shot prompting: Provide input-output examples when possible. If you cannot provide examples, detailed constraints become more important.

5W1H for prompts

Including the elements below improves stability.

Element What it means Example
What Target to improve “The Methods section below”
Why Purpose “To make it natural academic English”
How Criteria “Short subjects, passive voice, past tense”
How many Output count “Provide three options”
Constraints What not to do “Do not change meaning; do not add content”

Common prompt failures and fixes

Failure pattern Why it fails Better instruction
“Please fix this English.” Too vague, triggers a full rewrite “Only point out grammar and usage errors. No style changes.”
“Make it perfect English.” “Perfect” is undefined; may become overly formal “Make it natural for readers in [your field].”
“Translate this into English.” Can become literal; ignores section conventions “Write this as part of a Methods section in past tense, mostly passive.”
Too many constraints (10+) AI drops constraints Limit to 5 or fewer, put the most important first

Fix the claim in L1 first, then convert to English

When you struggle in English, it becomes easy to be pulled into AI-generated phrasing. A safer approach is to first stabilize what you want to say in your first language (L1). This is a practical version of the pre-editing approach in 2.3.

Steps:

  1. Write one conclusion sentence and two reasons in Japanese.
  2. Ask AI to convert it into English.
  3. Ask AI to check for deviation from the Japanese original.

Prompt example (Step 2):

Convert the following Japanese claim into natural English at around CEFR B2.
Use short sentences with clear subjects and verbs.
Do not add any new content.

[Japanese text]

Prompt example (Step 3):

Point out any parts of the English below that deviate from the original Japanese.
List the deviations in bullet points.

Japanese: [Japanese text]
English: [Generated English]

This keeps the division clear: content is yours; language support is AI’s.

Specify English level and refine step by step

Instead of expecting one prompt to produce a final version, use a staged process.

A three-stage refinement process

Stage Goal Main focus
Stage 1: Convert content into English Get correct meaning Accuracy, completeness
Stage 2: Adjust to academic style Fit section conventions subject length, hedging, tense, active/passive
Stage 3: Polish expressions Improve naturalness collocations, word choice, rhythm

Do not ask for everything at once

If you combine too many requirements, output becomes unstable. In one prompt, focus on one or two improvements.

Example: staged refinement (Stage 1 → Stage 2)

[Stage 1]
Convert the following Japanese into English that accurately conveys the meaning.
Prioritize accuracy over style.
Do not add new content.

[Japanese text]
[Stage 2]
Adjust the following English to academic style.

Improvements:
- Shorten long subjects
- Add appropriate hedging (not excessive)
- For a Methods section: use past tense and mostly passive voice

Do not change meaning.
Mark changes in **bold**.

[English from Stage 1]

What to do in Stage 3

In Stage 3, you should validate expressions against your field’s papers and corpora (see 2.2 Checking Conventional Expressions with Corpora). Use Google Scholar phrase searches and tools like AntConc to confirm that AI-suggested expressions are actually used in your discourse community.

Turn vocabulary and collocations into “your own list”

A useful approach is to move from “AI gives phrases” to “I reuse phrases intentionally.”

Suggest three places in the paragraph below where I can replace wording with widely used academic phrases.
For each suggestion, add:
(1) when it is appropriate to use, and
(2) one caution.

[Paragraph]

Then select only the phrases you plan to reuse, add them to a personal phrase list, and set a rule such as “Use at least two phrases from my list in the next writing session.”

Prompt: build a section-based personal phrase list

From the English below, extract reusable academic phrases and classify them by section:
- Introduction (background, gap, purpose)
- Methods (procedures, analysis)
- Results (reporting, figure/table reference)
- Discussion (interpretation, comparison, limitations)

For each category, provide 3–5 phrases and a one-line usage note.

[Your draft]

A practical mixed-language drafting workflow

One approach that works well for me in practice is:

  • Draft quickly, mixing Japanese and English as needed (use familiar field-standard terms and phrases).

  • Use AI to first make the English correct: I am writing an academic paper. Please translate the following sentences written in Japanese into natural English.

  • Then ask for a stronger refinement: Proofread this, significantly improving clarity and flow.

Because AI sees the full context, this can outperform pure machine translation, especially for technical academic writing.

Template library by purpose

Saving templates you use often improves efficiency. The templates below are general-purpose and are designed to leverage the style, tense, and logic guidance in 2.3.

Core templates by section

Template 1: Japanese (L1) → English conversion

Convert the following Japanese into natural academic English as a [SECTION NAME] section.

Constraints:
- Tense: [past / present / follow section conventions]
- Voice: [mostly passive / mostly active / mixed]
- Hedging: [add appropriately / do not add]
- Do not add new content
- Do not generate or invent citations

[Japanese text]

Template 2: Diagnose an English draft

Diagnose the following English as a [SECTION NAME] section.

For each item, write either OK or point out a concrete issue:
(1) Grammar and usage
(2) Tense conventions for the section
(3) Academic style (subject length, hedging, wordiness)
(4) Logical flow (sentence links)

For each issue, provide at most one suggested fix.

[English text]

Template 3: Generate paraphrase options

Paraphrase the TARGET below without changing meaning.
Provide 3 options. For each option, include:
1) best use case (one line)
2) formality level (high/medium/low)

TARGET:
<<<
[target expression]
>>>

CONTEXT:
<<<
[English with surrounding sentences]
>>>

Style improvement

Prompt: general academic style improvement

Revise the following English to academic style.
- Shorten the subject and bring the main verb earlier
- Add appropriate hedging
- Provide three alternatives and explain the differences in one line each
- Do not change meaning

[English text]

Prompt: Japanese (L1) → Introduction paragraph

Convert the following Japanese into a natural first paragraph of an English Introduction.
Keep the subject concise and use academic style.
Do not add new content.

[Japanese text]

Methods templates

Methods-specific templates (converting bullet points, participant description templates, removing vague wording, statistical reporting formats) are compiled in: 3.3 Writing the Methods Section

Prompt: detect and reduce wordiness

Identify all wordy or redundant expressions in the English below.
For each, provide:
(1) the quoted phrase
(2) a concise alternative
(3) a one-line reason

Do not change meaning.

[English text]

Proofreading

The prompts below are useful for proofreading, depending on how strongly you want AI to intervene.

Prompt: adjustable proofreading strength

A two-step approach often works well: broad proofreading first, then targeted constraints.

Step 1 (broad):

Proofread this, improving clarity and flow.

Stronger intervention:

Proofread this, significantly improving clarity and flow.

Light intervention:

Lightly proofread this.

Minimal intervention (typos/grammar only):

Proofread this (minimal requirements only).

Step 2 (add targeted checks):

Now please also check for:
- Overuse of passive voice in the Discussion section
- Hedging: is the strength appropriate to the claims?
- Consistency of tense within each paragraph

Prompt: revise only where definitely necessary

Proofread the following sentences and provide both the
original sentences and your suggested revisions. If they are
acceptable, you don't have to make suggestions. However,
when revisions are definitely necessary, please clearly indicate
what the original sentence was and how you recommend it
should be revised.

Add explicit criteria

Add criteria like the following to stabilize output.

Focus on:
- Grammar and punctuation errors
- Word choice appropriate for academic writing
- Conciseness (remove unnecessary words)

Prompt: shorten while preserving content

# Task
Suppose you're a professional proofreader. Your client asks you to
shorten the sentences by following these rules.

# Rules
1. Preserve the original wording as much as possible without
   sacrificing clarity or brevity.
2. Do not skip contained information.
3. Keep the quotes as they are.
4. Mark the changed parts so that they can be easily identified.

Tense and logical flow checks

Prompt: reporting verb tense check

Check the tense of reporting verbs used to cite prior research in the Introduction below.

Criteria:
- Specific author + year citations → past tense
- Summaries of multiple studies → present perfect
- Widely established knowledge → present tense

If there are problems, explain why and provide one fix per case.

[Introduction text]

Prompt: tense and logic check (paragraph)

Check the paragraph below for:
(1) tense consistency appropriate to the section (Methods/Results/Discussion)
(2) logical flow (gaps between sentences, overuse/underuse of connectors)

If there are problems, explain the fix strategy and provide one revised version only.

Section: [section name]
[Paragraph]

Prompt: causal language check

Check whether causal wording in the paragraph below could mislead readers.
If any sentence reads as “A causes B” when that is not warranted,
suggest one alternative phrasing.

[Paragraph]

Information structure and paragraph structure checks

Prompt: given-new and demonstratives

Check the paragraph below for:
(1) given-new flow (given information earlier, new information later)
(2) unclear “this” used alone (prefer “this + noun”)
(3) unclear reference of it/this/these/such

For each issue, explain why and provide one fix.

[Paragraph]

Prompt: paragraph structure check

For the paragraphs below, check:
(1) whether each paragraph has a clear topic sentence,
(2) whether each paragraph sticks to one topic,
(3) whether the sequence of topic sentences alone forms a coherent argument.

Identify problematic paragraphs and suggest improvement directions.
Do not rewrite.

[Text]

Prompt: detect logical leaps

Read the paragraph below as a first-time reader.
Check for:
(1) missing warrants (“why does this follow?”),
(2) unclear transitions between sentences,
(3) reliance on unstated assumptions.

For each, explain what information would make the logic explicit.
Do not rewrite.

[Paragraph]

Comprehensive checks

Prompt: style consistency

Check the manuscript below for style consistency.

Items:
(1) First-person use: consistent (we vs I), and active/passive switching is systematic
(2) Hedging: similar claim strength uses similar hedging strength

Point out inconsistencies and recommend a consistent choice.

[Manuscript]

Mechanical checks for target venue style (spelling variant, numbers, abbreviation rules) are summarized in:
4.1 Grammar and Style Checks

Prompt: comprehensive paragraph-quality check

Check the paragraph below across five dimensions.
For each, write OK or point out a concrete issue.

(1) Tense: appropriate and consistent for the section
(2) Information structure: follows given-new
(3) Logical flow: no leaps between sentences
(4) Connectors: appropriate and appropriately formal
(5) Paragraph structure: clear topic sentence, one topic

Section: [section name]
[Paragraph]

Prompt: paraphrase practice

Paraphrase the English below in three different ways without changing meaning.
For each version, explain the rewrite strategy in one line
(e.g., change the subject, use nominalization, restructure the sentence).

[Sentence]

Comparing and evaluating AI outputs

Even with the same prompt, different models or runs can produce different outputs. Learning how to compare outputs helps stabilize quality.

Evaluation dimensions

Dimension What to check Practical criterion
Accuracy no deviation from your intended meaning compare with your Japanese original
Naturalness fits academic English in your field compare with papers in your field
Specificity not overly generic includes your study-specific details
Consistency fits surrounding context read with other sections
Conciseness avoids redundancy can you shorten without loss?

Prompt: compare two AI outputs

The two English versions below were generated from the same Japanese.
Compare them on five dimensions and decide which is better for each.

Dimensions:
(1) accuracy, (2) academic naturalness, (3) specificity,
(4) contextual consistency, (5) conciseness

Japanese: [Japanese]
A: [Output A]
B: [Output B]

Using multiple AI models

Different models have different tendencies. It can be effective to choose models by purpose.

  • Learn tendencies by running the same prompt across models (ChatGPT, Claude, Gemini).
  • Allocate tasks by strengths (e.g., grammar checks vs paraphrase options).
  • Make the final choice yourself based on your field and your style.

See also: 4.1 Grammar and Style Checks.

When to stop refining

Refinement can be repeated endlessly, but over-refinement has costs:

  • Loss of authorial voice (the text becomes “generic”)
  • Drifting beyond Augmented Competence (you adopt expressions you cannot justify)
  • Diminishing returns (small gains after several rounds)

Practical stopping criteria

When the following are true, it is usually time to stop:

  • Meaning matches the Japanese original (no deviation)
  • Tense and voice match section conventions
  • You can explain every expression you use
  • Style is consistent with the surrounding sections
  • Feedback begins to feel like preference rather than improvement

If you still feel “it must get better” after five rounds

You may be adapting your judgment to AI output. Pause, and reread your own draft from the start.

Using saved custom instructions

Many AI tools allow you to save instructions so you do not have to repeat them each time. This is useful for repeated proofreading or for sharing common rules within a lab.

Tool Feature name Creating custom instructions Attach references Notes
ChatGPT GPTs often requires paid plan Yes Some public GPTs available broadly
Claude Projects often requires paid plan Yes
Gemini Gems often available Yes

If you store your target venue’s style guide and your own rules, you can dramatically shorten prompt setup.

Plans may change

Pricing and availability change frequently. Check official pages for the latest information.

Use a prompt-sharing site

Prompt Me-Mo lets you save prompts and share them. You can use it without signing in. Register the templates you use often so you can reuse them instantly while writing.

Prompt Me-Mo