Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking

TL;DR

This study investigates how GPT-2 models trained on synthetic data exhibit typological preferences in differential argument marking, revealing differences in modeling natural markedness direction versus object preference.

Contribution

It extends the analysis of typological preferences in language models to differential argument marking, highlighting distinct modeling behaviors for different typological dimensions.

Findings

Models prefer natural markedness direction, marking semantically atypical arguments.

Models do not replicate the human-like object preference in DAM.

Typological tendencies may stem from different underlying sources.

Abstract

Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities in human languages, particularly for syntactic phenomena such as word order. In this paper, we extend this paradigm to differential argument marking (DAM), a semantic licensing system in which morphological marking depends on semantic prominence. Using a controlled synthetic learning method, we train GPT-2 models on 18 corpora implementing distinct DAM systems and evaluate their generalization using minimal pairs. Our results reveal a dissociation between two typological dimensions of DAM. Models reliably exhibit human-like preferences for natural markedness direction, favoring systems in which overt marking targets semantically atypical arguments. In contrast, models do not reproduce the strong object preference in human languages, in which overt marking in DAM more often targets objects rather than subjects. These findings suggest that different typological tendencies may arise from distinct underlying sources.