Reasoning-Aware AIGC Detection via Alignment and Reinforcement

TL;DR

This paper presents REVEAL, a reasoning-based detection framework for AI-generated content that leverages a new multi-domain dataset and achieves state-of-the-art results through a two-stage training process.

Contribution

Introduction of REVEAL, a novel detection method that generates interpretable reasoning chains and employs reinforcement learning for improved accuracy and robustness.

Findings

REVEAL outperforms existing AIGC detection methods on multiple benchmarks.

The approach enhances logical consistency and reduces hallucinations in detection.

A comprehensive multi-domain dataset, AIGC-text-bank, supports diverse evaluation.

Abstract

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