Search papers, labs, and topics across Lattice.
This paper introduces REVEAL, a framework for AIGC detection that generates interpretable reasoning chains to improve classification accuracy and transparency. REVEAL employs a two-stage training process: supervised fine-tuning to enable reasoning, followed by reinforcement learning to enhance accuracy and logical consistency while mitigating hallucinations. Experiments on the newly introduced AIGC-text-bank dataset demonstrate that REVEAL achieves state-of-the-art performance in AIGC detection across multiple benchmarks.
Reasoning, not just text, is the key to detecting AI-generated content: REVEAL leverages interpretable reasoning chains to significantly outperform existing AIGC detectors.
The rapid advancement and widespread adoption of Large Language Models (LLMs) have elevated the need for reliable AI-generated content (AIGC) detection, which remains challenging as models evolve. We introduce AIGC-text-bank, a comprehensive multi-domain dataset with diverse LLM sources and authorship scenarios, and propose REVEAL, a detection framework that generates interpretable reasoning chains before classification. Our approach uses a two-stage training strategy: supervised fine-tuning to establish reasoning capabilities, followed by reinforcement learning to improve accuracy, improve logical consistency, and reduce hallucinations. Extensive experiments show that REVEAL achieves state-of-the-art performance across multiple benchmarks, offering a robust and transparent solution for AIGC detection. The project is open-source at https://aka.ms/reveal