Related papers: Language models align with brain regions that repr…

Analogical reasoning -- the capacity to identify and map structural relationships between different domains -- is fundamental to human cognition and learning. Recent studies have shown that large language models (LLMs) can sometimes match…

Progress in natural language processing (NLP) models that estimate representations of word sequences has recently been leveraged to improve the understanding of language processing in the brain. However, these models have not been…

This study investigates the linguistic understanding of Large Language Models (LLMs) regarding signifier (form) and signified (meaning) by distinguishing two LLM assessment paradigms: psycholinguistic and neurolinguistic. Traditional…

Over the years, many researchers have seemingly made the same observation: Brain and language model activations exhibit some structural similarities, enabling linear partial mappings between features extracted from neural recordings and…

Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in developing educational materials and designing public…

The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an alternative approach, concentrating on the quality of LM…

Large language models (LLMs) not only exhibit human-like performance but also share computational principles with the brain's language processing mechanisms. While prior research has focused on mapping LLMs' internal representations to…

Brain localization, which describes the association between specific regions of the brain and their corresponding functions, is widely accepted in the field of cognitive science as an objective fact. Today's large language models (LLMs)…

Large Language Models (LLMs) have recently been shown to produce estimates of psycholinguistic norms, such as valence, arousal, or concreteness, for words and multiword expressions, that correlate with human judgments. These estimates are…

Understanding the neural basis of language comprehension in the brain has been a long-standing goal of various scientific research programs. Recent advances in language modelling and in neuroimaging methodology promise potential…

Large Language Models (LLMs) have been shown to be effective models of the human language system, with some models predicting most explainable variance of brain activity in current datasets. Even in untrained models, the representations…

Language models (LMs) are known to represent the perspectives of some social groups better than others, which may impact their performance, especially on subjective tasks such as content moderation and hate speech detection. To explore how…

Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language processing? Results using a framework called Brain Score (BS) -- predicting fMRI…

Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…

Artificial Neural Networks, the building blocks of AI, were inspired by the human brain's network of neurons. Over the years, these networks have evolved to replicate the complex capabilities of the brain, allowing them to handle tasks such…

Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity. Progress in these models-through increased size, instruction-tuning, and…

Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…

Decoding language from the human brain remains a grand challenge for Brain-Computer Interfaces (BCIs). Current approaches typically rely on unimodal brain representations, neglecting the brain's inherently multimodal processing. Inspired by…

The representations generated by many models of language (word embeddings, recurrent neural networks and transformers) correlate to brain activity recorded while people read. However, these decoding results are usually based on the brain's…

This study investigates whether large language models (LLMs) mirror human neurocognition during abstract reasoning. We compared the performance and neural representations of human participants with those of eight open-source LLMs on an…