Saadia Gabriel

When Can LLMs Learn to Reason with Weak Supervision?

arXiv 2026

OpenThoughts: Data Recipes for Reasoning Models

arXiv 2025

MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations

arXiv 2025

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

arXiv 2025

ModelCitizens:Representing Community Voices in Online Safety

arXiv 2025

ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection

ACL 2022 5

Hamid Palangi

researcher

Salman Rahman

Ashima Suvarna

grad-student

Genglin Liu

Kai-Wei Chang

Thomas Hartvigsen

Yejin Choi

professor

Aaron Gokaslan

Achal Dave

Aditya Grover