Multilingual Language Models Predict Human Reading Behavior

Abstract

We analyze if large language models are able to predict patterns of human reading behavior. We compare the performance of language-specific and multilingual pretrained transformer models to predict reading time measures reflecting natural human sentence processing on Dutch, English, German, and Russian texts. This results in accurate models of human reading behavior, which indicates that transformer models implicitly encode relative importance in language in a way that is comparable to human processing mechanisms. We find that BERT and XLM models successfully predict a range of eye tracking features. In a series of experiments, we analyze the cross-domain and cross-language abilities of these models and show how they reflect human sentence processing.

Eyes Show the Way: Modelling Gaze Behaviour for Hallucination Detection

“…Eberle et al (2022) highlighted the inability of cognitive models to account for the higher level cognitive activities like semantic role matching, hence motivating the use of large language models (LLMs) for modelling the human gaze. Hollenstein et al (2021) showed the efficacy of LLMs in predicting the gaze features for multiple languages, including English, Russian, Dutch and German. Barrett et al (2018) used natural reading eye-tracking corpus for regularizing attention function in a multi-task setting.…”