Related papers: Selective Neuron Amplification in Transformer Lang…

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on…

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…

Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLMs) without retraining or adaptation efforts. However,…

A growing intuition in machine learning suggests a link between sparsity and interpretability. We introduce a novel self-ablation mechanism to investigate this connection ante-hoc in the context of language transformers. Our approach…

Masked language modeling (MLM) plays a key role in pretraining large language models. But the MLM objective is often dominated by high-frequency words that are sub-optimal for learning factual knowledge. In this work, we propose an approach…

Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor performance or misaligned behavior. One solution is to have humans provide a training signal by…

Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specifically designed for…

Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks. However, comprehending the underlying reasons for their effectiveness remains a challenging problem. Interpreting deep neural networks…

Transformers for language modeling usually rely on deterministic internal computation, with uncertainty expressed mainly at the output layer. We introduce variational neurons into Transformer feed-forward computation so that uncertainty…

Natural language inference (NLI) is among the most challenging tasks in natural language understanding. Recent work on unsupervised pretraining that leverages unsupervised signals such as language-model and sentence prediction objectives…

In reinforcement learning (RL), agents often operate in partially observed and uncertain environments. Model-based RL suggests that this is best achieved by learning and exploiting a probabilistic model of the world. 'Active inference' is…

Unseen or out-of-domain data can seriously degrade the performance of a neural network model, indicating the model's failure to generalize to unseen data. Neural net pruning can not only help to reduce a model's size but can improve the…

Recent developments in unsupervised representation learning have successfully established the concept of transfer learning in NLP. Mainly three forces are driving the improvements in this area of research: More elaborated architectures are…

Various natural language processing tasks are structured prediction problems where outputs are constructed with multiple interdependent decisions. Past work has shown that domain knowledge, framed as constraints over the output space, can…

Deep neural networks, and more recently large-scale generative models such as large language models (LLMs) and large vision-action models (LVAs), achieve remarkable performance across diverse domains, yet their prohibitive computational…

Transformer-based pre-trained language models have demonstrated superior performance on various natural language processing tasks. However, it remains unclear how the skills required to handle these tasks distribute among model parameters.…

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…

Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks. However, as demonstrated in recent literature, when tested on some simple adversarial examples, most of the models suffer…

Model-based methods and deep neural networks have both been tremendously successful paradigms in machine learning. In model-based methods, problem domain knowledge can be built into the constraints of the model, typically at the expense of…