Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapsby…
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmeticby Ruochen Jin, Bojian Hou, Jiancong…
Multiple Instance Verificationby Xin Xu, Eibe Frank, Geoffrey HolmesFirst submitted to arxiv on: 9 Jul…
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIby Yang Liu, Weixing…
Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewardsby Marco Mussi, Simone Drago,…
On the Power of Convolution Augmented Transformerby Mingchen Li, Xuechen Zhang, Yixiao Huang, Samet OymakFirst…
Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attentionby Tongzhou Liao, Barnabás PóczosFirst submitted to…
Just read twice: closing the recall gap for recurrent language modelsby Simran Arora, Aman Timalsina,…
Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Ratesby Shirley Kokane, Mostofa Rafid Uddin,…
Leveraging Graph Structures to Detect Hallucinations in Large Language Modelsby Noa Nonkes, Sergei Agaronian, Evangelos…