English

DependencyAI: Detecting AI Generated Text through Dependency Parsing

Computation and Language 2026-02-18 v1

Abstract

As large language models (LLMs) become increasingly prevalent, reliable methods for detecting AI-generated text are critical for mitigating potential risks. We introduce DependencyAI, a simple and interpretable approach for detecting AI-generated text using only the labels of linguistic dependency relations. Our method achieves competitive performance across monolingual, multi-generator, and multilingual settings. To increase interpretability, we analyze feature importance to reveal syntactic structures that distinguish AI-generated from human-written text. We also observe a systematic overprediction of certain models on unseen domains, suggesting that generator-specific writing styles may affect cross-domain generalization. Overall, our results demonstrate that dependency relations alone provide a robust signal for AI-generated text detection, establishing DependencyAI as a strong linguistically grounded, interpretable, and non-neural network baseline.

Keywords

Cite

@article{arxiv.2602.15514,
  title  = {DependencyAI: Detecting AI Generated Text through Dependency Parsing},
  author = {Sara Ahmed and Tracy Hammond},
  journal= {arXiv preprint arXiv:2602.15514},
  year   = {2026}
}
R2 v1 2026-07-01T10:39:49.546Z