5 papers
Playing repeated games with Large Language Models
Elif Akata, Lion Schulz, Julian Coda-Forno +3
LLMs are increasingly used in applications where they interact with humans and other agents. We propose to use behavioural game theory to study LLM's cooperation and coordination b…
Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
Luca Scimeca, Alexander Rubinstein, Damien Teney +2
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous…
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
Haritz Puerto, Martin Gubri, Sangdoo Yun +1
Membership inference attacks (MIA) attempt to verify the membership of a given data sample in the training set for a model. MIA has become relevant in recent years, following the r…
Scratching Visual Transformer's Back with Uniform Attention
Nam Hyeon-Woo, Kim Yu-Ji, Byeongho Heo +3
The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model…
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
Bálint Mucsányi, Michael Kirchhof, Seong Joon Oh
Uncertainty quantification, once a singular task, has evolved into a spectrum of tasks, including abstained prediction, out-of-distribution detection, and aleatoric uncertainty qua…