MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models (2403.01116v1)

Abstract: Pre-trained computational LLMs have recently made remarkable progress in harnessing the language abilities which were considered unique to humans. Their success has raised interest in whether these models represent and process language like humans. To answer this question, this paper proposes MulCogBench, a multi-modal cognitive benchmark dataset collected from native Chinese and English participants. It encompasses a variety of cognitive data, including subjective semantic ratings, eye-tracking, functional magnetic resonance imaging (fMRI), and magnetoencephalography (MEG). To assess the relationship between LLMs and cognitive data, we conducted a similarity-encoding analysis which decodes cognitive data based on its pattern similarity with textual embeddings. Results show that LLMs share significant similarities with human cognitive data and the similarity patterns are modulated by the data modality and stimuli complexity. Specifically, context-aware models outperform context-independent models as language stimulus complexity increases. The shallow layers of context-aware models are better aligned with the high-temporal-resolution MEG signals whereas the deeper layers show more similarity with the high-spatial-resolution fMRI. These results indicate that LLMs have a delicate relationship with brain language representations. Moreover, the results between Chinese and English are highly consistent, suggesting the generalizability of these findings across languages.