A systematic framework for generating novel experimental hypotheses from language models

Understand

Neural language models (LMs) have been shown to capture complex linguistic patterns, yet their utility in understanding human language and more broadly, human cognition, remains debated.

• While existing work in this area often evaluates human-machine alignment, few studies attempt to translate findings from this enterprise into novel insights about humans.
• To this end, we propose a systematic framework for hypothesis generation that uses LMs to simulate outcomes of experiments that do not yet exist in the literature.
• We instantiate this framework in the context of a specific research question in child language development: dative verb acquisition and cross-structural generalization.