Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
This work advances understanding of how LLMs relate to human language processing, with potential applications in cognitive science and AI, though it is incremental in refining existing methods.
The paper tackled the problem of understanding the alignment between large language models (LLMs) and human brain activity by introducing a fine-grained input attribution method to identify specific words important for brain-LLM alignment, revealing that brain alignment and next-word prediction rely on distinct word subsets with different biases and focuses.
Understanding the alignment between large language models (LLMs) and human brain activity can reveal computational principles underlying language processing. We introduce a fine-grained input attribution method to identify the specific words most important for brain-LLM alignment, and leverage it to study a contentious research question about brain-LLM alignment: the relationship between brain alignment (BA) and next-word prediction (NWP). Our findings reveal that BA and NWP rely on largely distinct word subsets: NWP exhibits recency and primacy biases with a focus on syntax, while BA prioritizes semantic and discourse-level information with a more targeted recency effect. This work advances our understanding of how LLMs relate to human language processing and highlights differences in feature reliance between BA and NWP. Beyond this study, our attribution method can be broadly applied to explore the cognitive relevance of model predictions in diverse language processing tasks.