On the Effectiveness of LLM-Specific Fine-Tuning for Detecting AI-Generated Text
This addresses authenticity verification challenges in education, publishing, and digital security, representing a strong incremental improvement over existing methods.
This paper tackled the problem of detecting AI-generated text by creating large-scale corpora and introducing per-LLM and per-LLM family fine-tuning strategies, achieving up to 99.6% token-level accuracy on a benchmark covering 21 large language models.
The rapid progress of large language models has enabled the generation of text that closely resembles human writing, creating challenges for authenticity verification in education, publishing, and digital security. Detecting AI-generated text has therefore become a crucial technical and ethical issue. This paper presents a comprehensive study of AI-generated text detection based on large-scale corpora and novel training strategies. We introduce a 1-billion-token corpus of human-authored texts spanning multiple genres and a 1.9-billion-token corpus of AI-generated texts produced by prompting a variety of LLMs across diverse domains. Using these resources, we develop and evaluate numerous detection models and propose two novel training paradigms: Per LLM and Per LLM family fine-tuning. Across a 100-million-token benchmark covering 21 large language models, our best fine-tuned detector achieves up to $99.6\%$ token-level accuracy, substantially outperforming existing open-source baselines.