[update] autorubric src

[XieLipeng0830]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @XieLipeng0830, 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 refines the reward modeling framework by standardizing terminology from 'principles' to 'rubrics' across all components and documentation. It also introduces a significant new 'Auto-Rubric' feature, which is a training-free system designed to automatically derive evaluation criteria from preference data. This enhancement aims to improve the clarity, efficiency, and interpretability of how model responses are assessed, providing a more robust foundation for reward model development and application.

Highlights

• Terminology Change: The term 'principles' has been consistently replaced with 'rubrics' across the entire codebase, including core reward model definitions, documentation, and example usage. This change reflects a refined conceptual framework for evaluating model responses.
• Introduction of Auto-Rubric Feature: A new 'Auto-Rubric' feature has been introduced, providing a training-free framework to automatically extract generalizable evaluation criteria (rubrics) from preference data. This aims to enhance the interpretability and efficiency of reward modeling.
• Comprehensive Tooling for Rubric Management: New scripts and modules have been added for the Auto-Rubric feature, covering rubric generation, iterative refinement, Maximal Coding Rate Reduction (MCR²) for optimal subset selection, and structuring into human-readable 'Theme-Tips' format, along with performance analysis tools.
• Documentation Updates: Extensive updates to the README.md, README_zh.md, docs/index.md, and various tutorial notebooks (.ipynb and .md files) reflect the new 'rubric' terminology and introduce the Auto-Rubric feature with detailed guides.

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 significant refactoring, replacing the term "Principle" with "Rubric" across the codebase to align with the new "Auto-Rubric" feature. The changes are extensive, touching documentation, code, and tests. Overall, the refactoring is well-executed and consistent. I've identified a few minor issues where the find-and-replace was overly broad, leading to incorrect terminology in specific contexts or a broken link in the documentation. My feedback focuses on correcting these instances to improve clarity and correctness. The addition of the Auto-Rubric feature and its associated documentation is a valuable enhancement.

[ployts]

LGTM