LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations Paper • 2410.02707 • Published 14 days ago • 44
RevisEval: Improving LLM-as-a-Judge via Response-Adapted References Paper • 2410.05193 • Published 10 days ago • 11
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search Paper • 2410.03864 • Published 12 days ago • 9
Inference Scaling for Long-Context Retrieval Augmented Generation Paper • 2410.04343 • Published 11 days ago • 8
Hyper-multi-step: The Truth Behind Difficult Long-context Tasks Paper • 2410.04422 • Published 11 days ago • 7
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention Paper • 2410.05076 • Published 10 days ago • 6
One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation Paper • 2410.07170 • Published 8 days ago • 15
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs Paper • 2410.05295 • Published 14 days ago • 12