A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles

TL;DR

This study systematically evaluates large language models' ability to understand argument roles in sentences, revealing they can distinguish plausible from implausible verb contexts but do not mimic human real-time processing patterns.

Contribution

It replicates psycholinguistic experiments to assess language models' sensitivity to argument roles and compares their processing to human sentence comprehension.

Findings

Models distinguish plausible and implausible verb contexts.

Models do not replicate human real-time processing patterns.

Capacity to detect verb plausibility differs from human mechanisms.

Abstract

We present a systematic evaluation of large language models' sensitivity to argument roles, i.e., who did what to whom, by replicating psycholinguistic studies on human argument role processing. In three experiments, we find that language models are able to distinguish verbs that appear in plausible and implausible contexts, where plausibility is determined through the relation between the verb and its preceding arguments. However, none of the models capture the same selective patterns that human comprehenders exhibit during real-time verb prediction. This indicates that language models' capacity to detect verb plausibility does not arise from the same mechanism that underlies human real-time sentence processing.