Related papers: Abstraction Induces the Brain Alignment of Languag…

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…

Brain-to-speech decoding models demonstrate robust performance in vocalized, mimed, and imagined speech; yet, the fundamental mechanisms via which these models capture and transmit information across different speech modalities are less…

Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear. This paper examines the gaps and overlaps between LMs and the brain at…

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire…

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained…

Artificial Intelligence (AI) systems based solely on neural networks or symbolic computation present a representational complexity challenge. While minimal representations can produce behavioral outputs like locomotion or simple…

Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this…

Recent cognitive modeling studies have reported that larger language models (LMs) exhibit a poorer fit to human reading behavior (Oh and Schuler, 2023b; Shain et al., 2024; Kuribayashi et al., 2024), leading to claims of their cognitive…

Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of these models are still opaque. In this paper, we aim to…

Pretrained language models are remarkably effective in aligning with human brain responses elicited by natural language stimuli, positioning them as promising model organisms for studying language processing in the brain. However, existing…

Speech and language models trained through self-supervised learning (SSL) demonstrate strong alignment with brain activity during speech and language perception. However, given their distinct training modalities, it remains unclear whether…

Many self-supervised speech models (S3Ms) have been introduced over the last few years, improving performance and data efficiency on various speech tasks. However, these empirical successes alone do not give a complete picture of what is…

The human brain extracts complex information from visual inputs, including objects, their spatial and semantic interrelations, and their interactions with the environment. However, a quantitative approach for studying this information…

As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble…

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at…

Understanding how humans process natural language has long been a vital research direction. The field of natural language processing (NLP) has recently experienced a surge in the development of powerful language models. These models have…

This article questions the widespread assumption that there are brain representations that will always remain unconscious in the sense of being inaccessible to individual awareness under any circumstances. This implies that some part of the…

Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…