LLM Reading List
FreeA paper & resource list of large language models.
FreeFree tier
About LLM Reading List
A curated GitHub repository that organizes papers, resources, and tools related to large language models (LLMs). It covers hot topics such as model training and optimization, alignment (e.g., RLHF), applications, principle analysis, technical improvements, surveys, and datasets. The repository also includes links to courses, demos, figures, and self-selected blog posts. The README is written in Chinese, targeting researchers and practitioners tracking the rapid progress in LLMs, particularly those exceeding 100 billion parameters. It emphasizes the role of compute in AI progress and references key works like GPT-4, InstructGPT, GLM-130B, and alignment research.
Key Features
Curated paper list covering LLM training, alignment, applications, and analysis
Includes courses, demos, figures, and blog posts
Organized into categories: model optimization, technical improvements, surveys, etc.
Tracks scaling laws, alignment techniques (RLHF, scalable oversight), and retrieval-augmented models
Open-source and freely accessible on GitHub
Pros & Cons
Pros
- Comprehensive collection spanning multiple LLM topics
- Organized into clear categories for easy navigation
- Includes both foundational papers and recent breakthroughs
- Free and open-source with community contributions possible
Cons
- README is primarily in Chinese, which may limit accessibility for non-Chinese speakers
- Repository may not be actively maintained or regularly updated (uncertain frequency)
- Lacks practical code implementations or tutorials for most papers
Best For
Staying updated on the latest LLM research and trendsEducational resource for students and researchers studying large language modelsReference for practitioners implementing or evaluating LLMsSurvey of alignment methods and training optimizations