相关论文: The stability and instability of the language cont…
Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment also generalize cross-linguistically, and what governs the variation? We test this using…
We provide an empirical study of the stability of recurrent neural networks trained to recognize regular languages. When a small amount of noise is introduced into the activation function, the neurons in the recurrent layer tend to saturate…
Dynamical networks with time delays can pose a considerable challenge for mathematical analysis. Here, we extend the approach of generalized modeling to investigate the stability of large networks of delay-coupled delay oscillators. When…
Word embeddings are powerful representations that form the foundation of many natural language processing architectures, both in English and in other languages. To gain further insight into word embeddings, we explore their stability (e.g.,…
Resting-state functional MRI (rs-fMRI) is a rich imaging modality that captures spontaneous brain activity patterns, revealing clues about the connectomic organization of the human brain. While many rs-fMRI studies have focused on static…
How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identified language-responsive brain regions across languages, but…
Adult language learning varies greatly among individuals. Traditionally associated with frontotemporal language regions, this variability is increasingly seen as stemming from distributed brain networks. However, the role of these networks…
Language confusion -- where large language models (LLMs) generate unintended languages against the user's need -- remains a critical challenge, especially for English-centric models. We present the first mechanistic interpretability (MI)…
Functional magnetic resonance imaging (fMRI) is widely used in clinical applications to highlight brain areas involved in specific cognitive processes. Brain impairments, such as tumors, suppress the fMRI activation of the anatomical areas…
In language production, humans are confronted with considerable word selection demands. Often, we must select a word from among similar, acceptable, and competing alternative words in order to construct a sentence that conveys an intended…
Early detection is crucial for timely intervention aimed at preventing and slowing the progression of neurocognitive disorder (NCD), a common and significant health problem among the aging population. Recent evidence has suggested that…
Functional magnetic resonance imaging (fMRI) is now a well-established technique for studying the brain. However, in many situations, such as when data are acquired in a resting state, it is difficult to know whether the data are truly…
Neural networks have become increasingly popular in controller design due to their versatility and efficiency. However, their integration into feedback systems can pose stability challenges, particularly in the presence of uncertainties.…
We examine whether large neural language models, trained on very large collections of varied English text, learn the potentially long-distance dependency of British versus American spelling conventions, i.e., whether spelling is…
Frequency is one of the major factors for training quality word embeddings. Several work has recently discussed the stability of word embeddings in general domain and suggested factors influencing the stability. In this work, we conduct a…
Many languages' inflectional morphological systems are replete with irregulars, i.e., words that do not seem to follow standard inflectional rules. In this work, we quantitatively investigate the conditions under which irregulars can…
Many studies in the neurosciences have dealt with the semantic processing of words or categories, but few have looked into the semantic organization of the lexicon thought as a system. The present study was designed to try to move towards…
Visual Language Models (VLMs) have achieved remarkable progress, yet their reliability under small, meaning-preserving input changes remains poorly understood. We present the first large-scale, systematic study of VLM robustness to benign…
Previous work has shown correlations between the hidden states of large language models and fMRI brain responses, on language tasks. These correlations have been taken as evidence of the representational similarity of these models and brain…
The existence of instabilities, for example in the form of adversarial examples, has given rise to a highly active area of research concerning itself with understanding and enhancing the stability of neural networks. We focus on a popular…