相关论文: Riding Brainwaves in LLM Space: Understanding Acti…

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…

Can large language model agents discover hidden safety objectives through experience alone? We introduce EPO-Safe (Experiential Prompt Optimization for Safe Agents), a framework where an LLM iteratively generates action plans, receives…

Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various…

Large language models (LLMs) exhibit remarkable similarity to neural activity in the human language network. However, the key properties of language shaping brain-like representations, and their evolution during training as a function of…

As large language models (LLMs) advance in their linguistic capacity, understanding how they capture aspects of language competence remains a significant challenge. This study therefore employs psycholinguistic paradigms in English, which…

Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance.…

Instruction tuning aligns the response of large language models (LLMs) with human preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling…

Adults vary greatly in how effectively they learn a new language, but the signals driving the learning processes and individual differences remain unclear. Over seven days, we tracked behavioral learning and collected fMRI data from 102…

Previous research has demonstrated the potential of using pre-trained language models for decoding open vocabulary Electroencephalography (EEG) signals captured through a non-invasive Brain-Computer Interface (BCI). However, the impact of…

Electroencephalography (EEG) signals reflect activities on certain brain areas. Effective classification of time-varying EEG signals is still challenging. First, EEG signal processing and feature engineering are time-consuming and highly…

To investigate how speech is processed in the brain, we can model the relation between features of a natural speech signal and the corresponding recorded electroencephalogram (EEG). Usually, linear models are used in regression tasks.…

A long-standing challenge in developing accurate recommendation models is simulating user behavior, mainly due to the complex and stochastic nature of user interactions. Towards this, one promising line of work has been the use of Large…

Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) is a direct communication pathway between the human brain and a computer. Most research so far studied more accurate BCIs, but much less attention has been paid…

Ambiguity is pervasive in real-world questions, yet large language models (LLMs) often respond with confident answers rather than seeking clarification. In this work, we show that question ambiguity is linearly encoded in the internal…

Current non-invasive neuroimaging techniques trade off between spatial resolution and temporal resolution. While magnetoencephalography (MEG) can capture rapid neural dynamics and functional magnetic resonance imaging (fMRI) can spatially…

In the fields of affective computing (AC) and brain-machine interface (BMI), the analysis of physiological and behavioral signals to discern individual emotional states has emerged as a critical research frontier. While deep learning-based…

Named entity recognition (NER) is a vital task in spoken language understanding, which aims to identify mentions of named entities in text e.g., from transcribed speech. Existing neural models for NER rely mostly on dedicated word-level…

Recently, large language models (LLMs) have achieved tremendous breakthroughs in the field of NLP, but still lack understanding of their internal neuron activities when processing different languages. We designed a method to convert dense…

User authentication is a pivotal element in security systems. Conventional methods including passwords, personal identification numbers, and identification tags are increasingly vulnerable to cyber-attacks. This paper suggests a paradigm…

Understanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent computational studies show that artificial neural language models spontaneously develop differentiated…