相关论文: Emergent Specialization: Rare Token Neurons in Lan…

Whether deep neural networks can exhibit emergent behaviour is not only relevant for understanding how deep learning works, it is also pivotal for estimating potential security risks of increasingly capable artificial intelligence systems.…

Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This study investigates two critical components believed to influence…

This work examines the presence of modularity in pre-trained Transformers, a feature commonly found in human brains and thought to be vital for general intelligence. In analogy to human brains, we consider two main characteristics of…

Functional differentiation in the brain emerges as distinct regions specialize and is key to understanding brain function as a complex system. Previous research has modeled this process using artificial neural networks with specific…

Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons in task-specific models contribute uniformly to task performance. In this work, we…

We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align…

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.…

Neural networks posses the crucial ability to generate meaningful representations of task-dependent features. Indeed, with appropriate scaling, supervised learning in neural networks can result in strong, task-dependent feature learning.…

We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…

While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual neurons. We present a technique called as Linguistic…

Neurons process sensory stimuli efficiently, showing sparse yet highly variable ensemble spiking activity involving structured higher-order interactions. Notably, while neural populations are mostly silent, they occasionally exhibit highly…

During language acquisition, children successively learn to categorize phonemes, identify words, and combine them with syntax to form new meaning. While the development of this behavior is well characterized, we still lack a unifying…

Neural language models predict the next token using a latent representation of the immediate token history. Recently, various methods for augmenting neural language models with an attention mechanism over a differentiable memory have been…

Advances in neural recording methods enable sampling from populations of thousands of neurons during the performance of behavioral tasks, raising the question of how recorded activity relates to the theoretical models of computations…

Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently understood. In this work, we show that across a wide range of open-weight Transformers, a…

Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…

Children's tendency to associate novel words with novel referents has been taken to reflect a bias toward mutual exclusivity. This tendency may be advantageous both as (1) an ad-hoc referent selection heuristic to single out referents…

This paper studies the emergence of interpretable categorical features within large language models (LLMs), analyzing their behavior across training checkpoints (time), transformer layers (space), and varying model sizes (scale). Using…

Neural language models often struggle with low-resource languages due to the limited availability of training data, making tokens from these languages rare in the training set. This paper addresses a specific challenge during training: rare…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…