awesome-language-model-analysis

github.com/furyton/awesome-language-model-analysis ↗

This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalization ability, and other properties of language models through theoretical analysis, empirical analysis, or a combination of both.

101

GitHub Stars

738

Curated Resources

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me in-context learning resources from awesome-language-model-analysis"

Installation instructions →

What's inside

Miscellanea

Phenomena of Interest

[paper link]In-Context Learning
[paper link]In-Context Learning
[paper link]In-Context Learning
[paper link]Learning / Generalization / Reasoning / Weak to Strong Generalization
[paper link]In-Context Learning
[paper link]In-Context Learning

Representational Capacity

[paper link]What Can Transformer Do? / Properties of Transformer
[paper link]What Can Transformer Not Do? / Limitation of Transformer
[paper link]What Can Transformer Do? / Properties of Transformer
[paper link]What Can Transformer Do? / Properties of Transformer
[paper link]What Can Transformer Do? / Properties of Transformer
[paper link]What Can Transformer Do? / Properties of Transformer

Architectural Effectivity

[paper link]Linear Attention / State Space Models / Recurrent Language Models / etc.
[paper link]Tokenization / Embedding
[paper link]Tokenization / Embedding
[paper link]Linear Attention / State Space Models / Recurrent Language Models / etc.
[paper link]Tokenization / Embedding
[paper link]Tokenization / Embedding

Mechanistic Engineering / Probing / Interpretability

Showing a sample of 738 resources. View the full list on GitHub →