Dissociable Neural Mechanisms for Human Inference Processing Predicted by Static and Contextual Language Models

Abstract

Language models (LMs) continue to reveal non-trivial relations to human language performance and the underlying neurophysiology. Recent research has characterized how word embeddings from a LM can be used to generate integrated discourse representations in order to perform inference on events. The current research investigates how such event knowledge may be coded in distinct manners in different classes of LMs and how this maps onto different forms of human inference processing. To do so, we investigate inference on events using two well documented human experimental protocols from Metusalem et al. 2012 and McKoon & Ratcliff 1986 (hereafter Metusalem and McKoon), compared with two protocols for simpler semantic processing. Interestingly, this reveals a dissociation in the relation between local semantics vs event-inference depending on the language models. In a series of experiments, we observed that for the static language models (word2vec/GloVe), there was a clear dissociation in the relation between semantics and inference for the two inference tasks. In contrast, for the contextual language models (BERT/RoBERTa), we observed a correlation between semantic and inference processing for both inference tasks. The experimental results suggest that inference as measured by Metusalem and McKoon rely on dissociable processes. While the static models are able to perform Metusalem inference, only the contextual models succeed in McKoon inference. Interestingly, these dissociable processes may be linked to well-characterized automatic vs strategic inferences processes in the psychological literature. This allows us to make predictions about dissociable neurophysiological markers that should be found during human inference processing with these tasks.