feat: add rephrasing prompts

[ChenZiHong-Gavin]

Pre-training Data: Improving Token Utility with Rephrasing

• https://arxiv.org/pdf/2507.20534

[gemini-code-assist]

Summary of Changes

Hello @ChenZiHong-Gavin, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly expands the content generation capabilities by introducing a comprehensive set of new rephrasing prompts. These additions enable the transformation of existing content into various specialized formats, catering to diverse audiences and communication objectives, from academic scrutiny to executive briefings and popular science explanations. The primary impact is to enhance the versatility and adaptability of generated text for different contexts.

Highlights

• Critical Analysis Rephrasing: Introduced templates for rephrasing content into a critical academic analysis, focusing on objective tone, structured content (summary, advantages, limitations, improvements), and strict citation/factual accuracy.
• Cross-Domain Analogy Rephrasing: Added templates to explain technical concepts using cross-domain analogies (e.g., biology, physics), aiming to lower understanding barriers while maintaining technical rigor and fidelity.
• Executive Summary Rephrasing: Implemented templates for generating executive summaries tailored for C-suite decision-makers, emphasizing strategic value, competitive advantages, resource needs, and business impact with concise, data-backed language.
• First-Person Narrative Rephrasing: Provided templates to transform technical documents into first-person practical experience sharing, suitable for blogs or internal sessions, integrating personal observations and real-world application scenarios.
• Historical Evolution Perspective Rephrasing: Created templates for reconstructing content from a technological history evolution perspective, outlining timelines, key breakthroughs, paradigm shifts, and future outlooks with strict temporal and factual accuracy.
• Popular Science Rephrasing: Added templates for rewriting technical documents as popular science articles for general readers, using engaging language, everyday analogies, and a 'problem-discovery-application' narrative.
• Q&A Dialogue Format Rephrasing: Introduced templates for restructuring technical documents into natural Q&A dialogues between an inquirer and an expert, ensuring logical progression, comprehensive coverage, and factual accuracy.
• Technical Deep Dive Rephrasing: Implemented templates for conducting in-depth technical analyses from a domain expert perspective, focusing on precise terminology, algorithmic complexity, system architecture trade-offs, and performance optimization.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a suite of rephrasing prompts, each tailored for a specific style and available in both English and Chinese. The new prompts are well-organized into separate files under graphgen/templates/rephrasing/. The implementation is clean, primarily defining string constants for the prompts. My review has identified a minor issue in one of the English prompt templates where Chinese characters were present, for which I've left a specific comment. Additionally, for better code organization and maintainability, I recommend adding an __init__.py file to the new graphgen/templates/rephrasing/ directory to make it a Python package. This file could also export all the newly defined prompt dictionaries, making them easier to import and use elsewhere in the project.