DeBERTa-Sentinel: Toward Transparent and Trustworthy Detection of AI-Generated Text
Muhammad Yousaf Rehman, Muhammad Islam
cs.CL, cs.AI
Submitted: 2026-08-02
Code: https://github.com/Galileo-Galili/HUMAN-VS-AI-TEXT-DETECTION
Project page: https://skylion007.github.io/OpenWebTextCorpus
License: http://creativecommons.org/licenses/by/4.0/
The gist: The rapid spread of large language models (LLMs) across the web raises concerns about misinformation, academic integrity, automated content manipulation, and risks to vulnerable online communities.
Terminology
Abstract
The rapid spread of large language models (LLMs) across the web raises concerns about misinformation, academic integrity, automated content manipulation, and risks to vulnerable online communities. Existing transformer-based detectors, such as GPT-Sentinel, show promise but struggle to generalize to diverse model outputs and paraphrasing attacks, limiting their role in building trustworthy web ecosystems. This work introduces DeBERTa-Sentinel, a responsible AI-generated text detection framework leveraging DeBERTa-v3's disentangled attention to capture subtle structural irregularities in synthetic content. A central design principle is transparency: unlike black-box commercial detectors, DeBERTa-Sentinel exposes token-level explanations of its decisions, enabling affected stakeholders journalists, educators, and platform trust and safety teams to audit, challenge, and contextualize detection outcomes. Using the GLC-AIText dataset of 28,057 human and LLM-generated samples (GPT, LLaMA, and Claude) with a 60-20-20 split, DeBERTa-Sentinel achieves 98.21% validation accuracy and surpasses the RoBERTa-Sentinel baseline from NeurIPS 2025, achieving 97.53% test accuracy, 95.89% precision, 99.33% recall, and 99.53% ROC-AUC, and maintaining a 0.665% false negative rate. The model's interpretability reveals linguistic markers such as academic phrasing and formal transitions associated with synthetic text, directly supporting stakeholder needs for verifiable, auditable content-authenticity decisions. By advancing responsible detection methods that reduce bias and enhance explainability, DeBERTa-Sentinel promotes trustworthy, ethical, and human-centric AI systems. Code and data are available at https://github.com/Galileo-Galili/HUMAN-VS-AI-TEXT-DETECTION.
Sources
- LLaMA: Open and Efficient Foundation Language Models
- Unified Large Language Models for Misinformation Detection in Low-Resource Linguistic Settings
- Release Strategies and the Social Impacts of Language Models
- GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content
- HULLMI: Human vs LLM identification with explainability
- Can AI-Generated Text be Reliably Detected?
- A Survey on Detection of LLMs-Generated Content
- Training language models to follow instructions with human feedback
- Constitutional AI: Harmlessness from AI Feedback
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering