In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors …
Because" out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to …
Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present …
N Carlini, M Nasr… - Advances in …, 2024 - proceedings.neurips.cc
Large language models are now tuned to align with the goals of their creators, namely to be" helpful and harmless." These models should respond helpfully to user questions, but refuse …
A Mao, M Mohri, Y Zhong - International conference on …, 2023 - proceedings.mlr.press
Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss applied to the outputs of a neural network, when the softmax is used. But, what guarantees …
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative …
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of data distributions when performing zero-shot inference (ie, without fine-tuning on a specific …
Recent work argues that robust training requires substantially larger datasets than those required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a …