# Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy

arXiv: https://arxiv.org/abs/2603.23146 · HTML: https://mlsanity.com/paper/2603.23146/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 15 of 15)

- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [Ghostbuster: Detecting Text Ghostwritten by Large Language Models](https://mlsanity.com/paper/2305.15047/) (2023)
- [SemEval-2024 Task 8: Multidomain, Multimodel and Multilingual Machine-Generated Text Detection](https://mlsanity.com/paper/2404.14183/) (2024)
- [Towards Possibilities & Impossibilities of AI-generated Text Detection: A Survey](https://mlsanity.com/paper/2310.15264/) (2023)
- [StyloAI: Distinguishing AI-Generated Content with Stylometric Analysis](https://mlsanity.com/paper/2405.10129/) (2024)
- [Exploring the Limitations of Detecting Machine-Generated Text](https://mlsanity.com/paper/2406.11073/) (2024)
- [Detecting Machine-Generated Texts: Not Just "AI vs Humans" and Explainability is Complicated](https://mlsanity.com/paper/2406.18259/) (2024)
- [GenAI Content Detection Task 1: English and Multilingual Machine-Generated Text Detection: AI vs. Human](https://mlsanity.com/paper/2501.11012/) (2025)
- [Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text](https://mlsanity.com/paper/2501.03212/) (2025)
- [Linguistic Characteristics of AI-Generated Text: A Survey](https://mlsanity.com/paper/2510.05136/) (2025)
- [mdok of KInIT: Robustly Fine-tuned LLM for Binary and Multiclass AI-Generated Text Detection](https://mlsanity.com/paper/2506.01702/) (2025)
- [LuxVeri at GenAI Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of AI-Generated Text across English and Multilingual Contexts](https://mlsanity.com/paper/2501.11914/) (2025)

## Built on by (most cited first, 2 of 2)

- [Show, Don't TELL: Explainable AI-Generated Text Detection](https://mlsanity.com/paper/2605.27921/) (2026)
- [A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID](https://mlsanity.com/paper/2609.30287/) (2026)

## Abstract (arXiv)

The widespread adoption of Large Language Models (LLMs) has made the detection of AI-Generated text a pressing and complex challenge. Although many detection systems report high benchmark accuracy, their reliability in real-world settings remains uncertain, and their interpretability is often unexplored. In this work, we investigate whether contemporary detectors genuinely identify machine authorship or merely exploit dataset-specific artefacts. We propose an interpretable detection framework that integrates linguistic feature engineering, machine learning, and explainable AI techniques. When evaluated on two prominent benchmark corpora, namely PAN CLEF 2025 and COLING 2025, our model trained on 30 linguistic features achieves leaderboard-competitive performance, attaining an F1 score of 0.9734. However, systematic cross-domain and cross-generator evaluation reveals substantial generalisation failure: classifiers that excel in-domain degrade significantly under distribution shift. Using SHAP- based explanations, we show that the most influential features differ markedly between datasets, indicating that detectors often rely on dataset-specific stylistic cues rather than stable signals of machine authorship. Further investigation with in-depth error analysis exposes a fundamental tension in linguistic-feature-based AI text detection: the features that are most discriminative on in-domain data are also the features most susceptible to domain shift, formatting variation, and text-length effects. We believe that this knowledge helps build AI detectors that are robust across different settings. To support replication and practical use, we release an open-source Python package that returns both predictions and instance-level explanations for individual texts.