DeBERTa-Sentinel: Toward Transparent and Trustworthy Detection of AI-Generated Text

• URL: http://arxiv.org/abs/2608.01046v1
• Date: Sun, 02 Aug 2026 07:08:20 GMT
• Title: DeBERTa-Sentinel: Toward Transparent and Trustworthy Detection of AI-Generated Text
• Abstract summary: This work introduces DeBERTa-Sentinel, a responsible AI-generated text detection framework.<n>Unlike black-box commercial detectors, DeBERTa-Sentinel exposes token-level explanations of its decisions.<n>DeBERTa-Sentinel achieves 98.21% validation accuracy and surpasses the RoBERTa-Sentinel baseline from NeurIPS 2025.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Self-Verifying Anomaly Detection using Explainable AI for Cybersecurity of DER Networks [0.0]
  This paper presents an XAI-based anomaly detection framework tailored for Distributed Energy Resources (DERs) networks.<n>The proposed framework uses a self-verifying mechanism that validates ADS alerts to ensure trustworthy decision-making.<n>Experiments on a realistic DNP3 dataset achieved over 98% detection accuracy, an average rule--SHAP consistency of 44.6%, a SHAP latency of 14.5 ms per alert, and a confidence deviation within 5%.
  arXiv  Detail & Related papers  (2026-09-11T00:19:59Z)
• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems [1.7327102304628392]
  Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge.<n>We propose an Evaluation Agent that combines Natural Language Inference (NLI) factual verification, a five-signal poison detector with relevance-weighted aggregation, and a Trust Index T = 0.4 F + 0.35 C + 0.25 (1 - P )<n>On TruthfulQA with Llama 3.3 70B, the agent reaches 91% accuracy and 100% precision, with 100% recall on instruction injection.
  arXiv  Detail & Related papers  (2026-08-21T13:42:41Z)
• Cybersecurity Detection Classification with Reasoning-enabled Language Models [50.72675435043546]
  A major issue in Security Operations Centers (SOCs) is alert fatigue.<n>Prior work prompts or fine-tunes large language models (LLMs) to emit a triage label directly, but does not train them to reason about whether a detection is a genuine threat.<n>We train a chain-of-thought (CoT) reasoning-enabled triage classifier on real, human-labeled Windows endpoint detections.
  arXiv  Detail & Related papers  (2026-07-30T16:22:13Z)
• DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis [13.9689104714669]
  DSIPA is a training-free framework that detects large language models (LLMs) content by quantifying sentiment distributional stability under controlled stylistic variation.<n>It operates in a zero-shot, black-box manner, leveraging two unsupervised metrics, sentiment distribution consistency and sentiment distribution preservation.<n>Our framework exhibits superior generalizability across domains and strong resilience to adversarial conditions.
  arXiv  Detail & Related papers  (2026-04-29T06:22:08Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions [59.49967357689445]
  Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies.<n>This study presents a complete open-source dilated real-based framework for the development and validation of deep learning models for affective touch recognition in soft interactive companions.
  arXiv  Detail & Related papers  (2026-04-16T10:20:05Z)
• Do You Trust Me? Cognitive-Affective Signatures of Trustworthiness in Large Language Models [12.714909005419964]
  We analyze how large language models encode perceived trustworthiness in web-like narratives.<n>Across models, systematic layer- and head-level activation differences distinguish high- from low-trust texts.<n>Strongest associations emerge with appraisals of fairness, certainty, and accountability-self.
  arXiv  Detail & Related papers  (2025-12-17T08:47:23Z)
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• Diversity Boosts AI-Generated Text Detection [51.56484100374058]
  DivEye is a novel framework that captures how unpredictability fluctuates across a text using surprisal-based features.<n>Our method outperforms existing zero-shot detectors by up to 33.2% and achieves competitive performance with fine-tuned baselines.
  arXiv  Detail & Related papers  (2025-09-23T10:21:22Z)
• VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation [6.576811224645293]
  Graph Neural Networks (GNNs) can learn structural and logical code relationships in a data-driven manner.<n>GNNs often learn'spurious' correlations from superficial code similarities.<n>We propose a unified framework for robust and interpretable vulnerability detection, called VISION.
  arXiv  Detail & Related papers  (2025-08-26T11:20:39Z)
• A Hybrid DeBERTa and Gated Broad Learning System for Cyberbullying Detection in English Text [0.356008609689971]
  cyberbullying affects approximately 54.4% of teenagers according to recent research.<n>This paper presents a hybrid architecture that combines the contextual understanding capabilities of transformer-based models with the pattern recognition strengths of broad learning systems for effective cyberbullying detection.
  arXiv  Detail & Related papers  (2025-06-19T06:15:22Z)
• Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classification [9.818997495801705]
  This paper presents a unified framework called Explainability-driven Detection, Identification, and Transformation (EDIT) to strengthen inference-time defenses.<n>EDIT integrates explainability tools, including attention maps and integrated gradients, with frequency-based features to automatically detect and identify adversarial perturbations.<n>The framework provides robust, interpretable, and efficient protection against both standard, zero-day, and adaptive adversarial threats in text classification models.
  arXiv  Detail & Related papers  (2023-07-03T03:17:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.