Awesome-LLM-Post-training
Awesome Reasoning LLM Tutorial/Survey/Guide
What is Awesome-LLM-Post-training?
Awesome Reasoning LLM Tutorial/Survey/Guide
Overview of Awesome-LLM-Post-training
What it is
This repository is a curated collection of papers, code implementations, benchmarks, and resources related to Large Language Models (LLMs) post-training methodologies. It includes a taxonomy of post-training approaches categorized into fine-tuning, reinforcement learning, and test-time scaling methods. The repository is based on a survey paper titled 'LLM Post-Training: A Deep Dive into Reasoning Large Language Models,' which has been accepted for publication in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
Key features
- Curated list of influential papers on LLM post-training, including surveys, theory, and explainability.
- Taxonomy covering fine-tuning, reinforcement learning, and test-time scaling approaches.
- Sections on LLMs in reinforcement learning, reward learning (process reward models), policy optimization, and reasoning.
- Includes resources on multi-agent RL, exploration, generalization, and applications.
- Organized table of contents with subsections for papers, tutorials, libraries, and other resources.
Use cases
Researchers and practitioners seeking a comprehensive overview of post-training techniques for LLMs, including reinforcement learning from human feedback, process reward models, and reasoning enhancement. Useful for staying updated with the latest advancements in LLM reasoning and decision-making.
Getting started
See the repository README for details on navigating the curated list and accessing the referenced papers and resources.
License and pricing
The license is not stated in the repository metadata. The repository is listed as open source.
Based on the project's public README and repository metadata.