Probing Large Language Models from A Human Behavioral Perspective

arXiv:2310.05216v2 Announce Type: replace
Abstract: Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. However, the understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention (MHSA), remains largely unexplored. In this work, we probe LLMs from a human behavioral perspective, correlating values from LLMs with eye-tracking measures, which are widely recognized as meaningful indicators of human reading patterns. Our findings reveal that LLMs exhibit a similar prediction pattern with …

abstract arxiv attention cs.cl foundational foundational models head however human language language models large language large language models llms modern multi-head networks nlp perspective prediction probe processes self-attention type understanding work