Denny Zhou

Larger language models do in-context learning differently

Simple synthetic data reduces sycophancy in large language models

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Large Language Models as Optimizers

Large Language Models Cannot Self-Correct Reasoning Yet

Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models

Chain-of-Thought Reasoning Without Prompting

Best Practices and Lessons Learned on Synthetic Data

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

Teaching Large Language Models to Self-Debug

Large Language Models as Analogical Reasoners

SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures

Large Language Models can Learn Rules

Large Language Models as Tool Makers

Larger language models do in-context learning differently