👋

Welcome to Science of LLM Blog

We are the PKU Interpretable Large Language Model And Reasoning (PILLAR) Group at Peking University. Our goal is to uncover the mechanisms behind large language models and use that understanding to build trustworthy models that are reliable, truthful, and safe.

This blog shares our latest research insights, findings, and thoughts on large language models, interpretability, reasoning, and trustworthy AI. We document our journey of understanding AI through AI, exploring everything from internal representations to model behaviors.

Mechanistic Understanding

Trustworthy AI

Research Insights

Scientific Exploration

Understanding Large Language Models - An Introduction

January 15, 2025 Research Team 5 min read

This is an example blog post demonstrating the format for Science of LLM Blog posts. Replace this with your actual content.

LLM Research Introduction