FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs Paper • 2410.02899 • Published Oct 3, 2024 • 1
Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems Paper • 2609.39050 • Published Sep 30 • 9
Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems Paper • 2609.39050 • Published Sep 30 • 9
CIDAR: Culturally Relevant Instruction Dataset For Arabic Paper • 2402.03177 • Published Feb 5, 2024 • 8