Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps Paper • 2407.07071 • Published Jul 9 • 11
From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty Paper • 2407.06071 • Published Jul 8 • 7
ORPO: Monolithic Preference Optimization without Reference Model Paper • 2403.07691 • Published Mar 12 • 63