Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs

TL;DR

This paper introduces an image-semantic guided detection method that enhances LLMs' ability to identify AI-generated modern Chinese poetry by integrating visual content with textual analysis, achieving state-of-the-art results.

Contribution

It proposes a novel image-semantic guided approach for detecting AI-generated poetry, significantly improving detection accuracy over traditional text-only methods.

Findings

The Gemini detector with our method achieves a Macro-F1 score of 85.65%.

Our method outperforms baseline detectors and traditional methods like RoBERTa.

Performance improvements are consistent across multiple LLM-generated datasets.

Abstract

Previous detection studies have shown that LLMs cannot be effectively used as detectors, but these studies have not addressed modern Chinese poetry. Moreover, no relevant research has explored the performance of LLMs in detecting modern Chinese poetry. This paper evaluates and enhances the performance of LLMs as detectors for modern Chinese poetry, and proposes an image-semantic guided poetry detection method. Compared with traditional detection approaches, our method innovatively incorporates images that reflect the content of the poetry. Through example-driven approaches, our method effectively integrates information such as meaning, imagery, and feeling from the image, then forms a complementary judgment with the poem text. Experimental results demonstrate that the LLM detectors based on our method outperform baseline detectors based on plain text, and even surpass the best-performing traditional detector, RoBERTa. The Gemini detector using our method achieves a Macro-F1 score of 85.65%, reaching the state-of-the-art level. The performance improvements of different LLM detectors on multiple LLMs-generated data prove the effectiveness of our method.