Alon Albalak

OpenThoughts: Data Recipes for Reasoning Models

arXiv 2025

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

arXiv 2025

Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

arXiv 2025

A Survey on Data Selection for Language Models

arXiv 2024

RWKV: Reinventing RNNs for the Transformer Era

arXiv 2023

Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning

arXiv 2023

Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data

improving-few-shot-generalization-by

Colin Raffel

William Yang Wang

Aaron Gokaslan

Guangyu Song

Liangming Pan

Niklas Muennighoff

grad-student

Shayne Longpre

researcher

Stella Biderman

founder

Tatsunori Hashimoto

professor

Xinyi Wang