IAAR-Shanghai/ICSFSurvey

Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

24
/ 100
Experimental

This project is a comprehensive survey that explores how Large Language Models (LLMs) can evaluate and improve their own performance. It helps AI researchers, machine learning engineers, and data scientists understand methods to reduce incorrect outputs (hallucinations) and enhance reasoning abilities in LLMs. The project provides a curated list of research papers and experimental results demonstrating consistency measurement and response analysis.

172 stars. No commits in the last 6 months.

Use this if you are an AI researcher or practitioner looking to understand the current landscape of self-correction, self-refinement, and hallucination alleviation techniques in large language models.

Not ideal if you are looking for an out-of-the-box software tool to directly apply to your LLM projects without diving into research papers.

Large Language Models AI Research Machine Learning Engineering Natural Language Processing AI Ethics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

172

Forks

4

Language

Jupyter Notebook

License

Last pushed

Dec 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/IAAR-Shanghai/ICSFSurvey"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.