Tag
This paper describes two pre-specified empirical tests to evaluate whether phase-derived features improve prediction accuracy for commitment or contradiction endpoints, but results show no significant improvement over baseline models.
This paper investigates whether large language models encode syntactic abstractions like phase boundaries that are not captured by Universal Dependencies, using structural probes on wh-movement stimuli with invariant UD distances, finding evidence across 13 LLMs for phase-structure representations that are causally active.