DIALOG-22 RuATD: Generated Text Detection
Abstract
This paper presents our approach to the DIALOG-22 RuATD shared task on detecting artificially generated Russian text. We develop machine learning classifiers to distinguish between human-written and AI-generated content, achieving competitive results on the benchmark.
Key Contributions
- Russian-specific detection: Methods tailored for Russian language AI text detection
- Feature engineering: Linguistic and statistical features for classification
- Model comparison: Evaluation of transformer-based and classical approaches
- Benchmark results: Competitive performance on RuATD dataset
Relevance Today
With the proliferation of ChatGPT and other LLMs, detecting AI-generated text has become crucial for academic integrity, content moderation, and misinformation prevention. This early work on Russian text detection established important baselines for the field.
Related Topics
Low-Resource Text Classification · LLM Security · Trojan Detection
📄 Access the Paper:
View on Google Scholar