A systematic framework for generating novel experimental hypotheses from language models

ArXi:2408.05086v3 Announce Type: replace Neural language models (LMs) have been shown to capture complex linguistic patterns, yet their utility in understanding human language and 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.