Along with the great success of deep neural networks, there is also growing concern about
their black-box nature. The interpretability issue affects people's trust on deep learning …

The field of natural language processing has seen impressive progress in recent years, with
neural network models replacing many of the traditional systems. A plethora of new models …

Large language models (LLMs) have demonstrated impressive capabilities in natural
language processing. However, their internal mechanisms are still unclear and this lack of …

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role
in the network remains under-explored. We show that feed-forward layers in transformer …

Pre-trained language models can be surprisingly adept at tasks they were not explicitly
trained on, but how they implement these capabilities is poorly understood. In this paper, we …

Trust is a central component of the interaction between people and AI, in that'incorrect'levels
of trust may cause misuse, abuse or disuse of the technology. But what, precisely, is the …

Despite rapid adoption and deployment of large language models (LLMs), the internal
computations of these models remain opaque and poorly understood. In this work, we seek …

The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

Some neurons in deep networks specialize in recognizing highly specific perceptual,
structural, or semantic features of inputs. In computer vision, techniques exist for identifying …

Transfer-learning methods aim to improve performance in a data-scarce target domain using
a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing …