# SKDU at De-Factify 4.0: Natural Language Features for AI-Generated Text-Detection

arXiv: https://arxiv.org/abs/2503.22338 · HTML: https://mlsanity.com/paper/2503.22338/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Builds on (most cited first, 6 of 6)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [This Just In: Fake News Packs a Lot in Title, Uses Simpler, Repetitive Content in Text Body, More Similar to Satire than Real News](https://mlsanity.com/paper/1703.09398/) (2017)
- [Raidar: geneRative AI Detection viA Rewriting](https://mlsanity.com/paper/2401.12970/) (2024)
- [A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization](https://mlsanity.com/paper/2403.01152/) (2024)
- [StyloAI: Distinguishing AI-Generated Content with Stylometric Analysis](https://mlsanity.com/paper/2405.10129/) (2024)
- [On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection](https://mlsanity.com/paper/2305.12829/) (2023)

## Built on by (most cited first, 1 of 1)

- [Findings of the Counter Turing Test: AI-Generated Text Detection](https://mlsanity.com/paper/2605.20761/) (2026)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) has introduced new challenges in distinguishing human-written text from AI-generated content. In this work, we explored a pipelined approach for AI-generated text detection that includes a feature extraction step (i.e. prompt-based rewriting features inspired by RAIDAR and content-based features derived from the NELA toolkit) followed by a classification module. Comprehensive experiments were conducted on the Defactify4.0 dataset, evaluating two tasks: binary classification to differentiate human-written and AI-generated text, and multi-class classification to identify the specific generative model used to generate the input text. Our findings reveal that NELA features significantly outperform RAIDAR features in both tasks, demonstrating their ability to capture nuanced linguistic, stylistic, and content-based differences. Combining RAIDAR and NELA features provided minimal improvement, highlighting the redundancy introduced by less discriminative features. Among the classifiers tested, XGBoost emerged as the most effective, leveraging the rich feature sets to achieve high accuracy and generalisation.