EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Statistical Fingerprinting Beyond Token Distributions Using Syntactic and Discourse-Level Signatures for LLM Authentication

Yongjie Lin, Zihan Cui, Alexander Monroe

American Journal of Business, Commerce and Economics · 2026

DOI: 10.71465/ajbce3554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Business, Commerce and Economics, 2026. Verfasst von Yongjie Lin und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid proliferation of Large Language Models (LLMs) has created unprecedented challenges in content authentication and model attribution. Traditional statistical fingerprinting methods primarily rely on token-level distribution patterns, which are increasingly vulnerable to adversarial manipulation and model fine-tuning. This research introduces a novel multi-layered fingerprinting framework that extends beyond superficial token distributions to incorporate syntactic structures and discourse-level signatures for robust LLM authentication. We propose a hierarchical feature extraction methodology that captures deep linguistic patterns including dependency parsing structures, semantic coherence measures, and discourse relationship markers. Our experimental evaluation across multiple state-of-the-art LLMs demonstrates that syntactic and discourse-level features provide significantly higher discriminative power compared to traditional token-based approaches, achieving 94.7% authentication accuracy even under adversarial conditions. The framework introduces three key innovations: syntactic tree embedding for structural fingerprinting, discourse graph construction for rhetorical pattern analysis, and temporal coherence modeling for stylistic consistency verification. Results indicate that combining multiple linguistic levels creates robust signatures resistant to common evasion techniques while maintaining computational efficiency for real-world deployment. This work establishes foundational principles for next-generation LLM authentication systems that can adapt to evolving model architectures and generation strategies.

Zitieren

APA

Lin, Y., Cui, Z., & Monroe, A. (2026). Statistical Fingerprinting Beyond Token Distributions Using Syntactic and Discourse-Level Signatures for LLM Authentication. American Journal of Business, Commerce and Economics. https://doi.org/10.71465/ajbce3554

Vancouver

Lin Y, Cui Z, Monroe A. Statistical Fingerprinting Beyond Token Distributions Using Syntactic and Discourse-Level Signatures for LLM Authentication. American Journal of Business, Commerce and Economics. 2026. doi:10.71465/ajbce3554

BibTeX
@article{Lin2026,
  author = {Lin, Yongjie and Cui, Zihan and Monroe, Alexander},
  title = {Statistical Fingerprinting Beyond Token Distributions Using Syntactic and Discourse-Level Signatures for LLM Authentication},
  journal = {American Journal of Business, Commerce and Economics},
  year = {2026},
  doi = {10.71465/ajbce3554}
}
Kostenlos starten →