Quoc V Le

EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration

Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs

Evolve: Evaluating and Optimizing LLMs For Exploration

Simple synthetic data reduces sycophancy in large language models

Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

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

Long-form factuality in large language models

Large Language Models as Optimizers

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

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