Exploring Gaps in the APS: Direct Minimal Pair Analysis in LLM Syntactic Assessments
This work addresses the challenge of accurately evaluating LLMs' syntactic abilities for researchers in computational linguistics, though it is incremental as it refines existing methods.
This paper tackled the problem of assessing Large Language Models' syntactic competence by comparing direct minimal pair analysis with Difference-in-Differences metrics, finding that GPT-2 succeeds across all four tested conditions for parasitic gaps, indicating robust knowledge of filler-gap licensing principles.
Recent studies probing the Argument from the Poverty of the Stimulus (APS) have applied Large Language Models (LLMs) to test the learnability of complex syntax through surprisal-based metrics. However, divergent conclusions raise questions concerning the insights these metrics offer. While Wilcox et al. (2024) used direct minimal pair comparisons (the "wh-effect") to demonstrate that models successfully generalise knowledge of filler-gap dependencies, Lan et al. (2024) used a Difference-in-Differences (DiD) metric and found that models largely fail on parasitic gaps (PGs). This paper argues that the direct minimal pair approach offers greater diagnostic transparency. We demonstrate this by generating a full 8-permutation paradigm of refined PG stimuli and evaluating the GPT-2 model used in previous studies with a systematic Wilcox-style wh-effect analysis. Our results show that GPT-2 succeeds across all four tested conditions, indicating robust knowledge of filler-gap licensing principles even in complex PG environments. This finding, which contrasts with the more ambiguous results from DiD-style metrics, suggests that the choice of evaluation metric is critical for assessing an LLM's syntactic competence.