distilled Self-Critique refines the outputs of a LLM with only synthetic data
-
Updated
Apr 11, 2024 - Jupyter Notebook
#
self-critique
Here are 6 public repositories matching this topic...
A Claude Code plugin that adds adversarial self-critique to every task. Claude scores its own work across multiple dimensions, identifies weaknesses, and proposes improvements — before you ship anything.
-
Updated
Feb 26, 2026 - Shell
MetaSC: Test-Time Safety Specification Optimization for Language Models
-
Updated
Mar 6, 2025 - Python
"Merging Improves Self-Critique Against Jailbreak Attacks", code and models
-
Updated
Jul 5, 2024 - Jupyter Notebook
AI planning platform using LLM intrinsic self-critique.
-
Updated
Jan 10, 2026 - Python
Implementation of the Self-Critique Chain pattern for automated research paper summarization using Claude AI.
python nlp api docker machine-learning monitoring pipeline text-summarization summarization production-ready claude mlops mlflow fastapi research-papers llm prompt-engineering anthropic self-critique chain-of-verification
-
Updated
Nov 18, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the self-critique topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the self-critique topic, visit your repo's landing page and select "manage topics."