Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs
For researchers and practitioners in AI-generated text detection, this work provides a novel approach for detecting AI-generated modern Chinese poetry, a previously unaddressed domain.
This paper addresses the detection of AI-generated modern Chinese poetry, proposing an image-semantic guided method that incorporates images reflecting poem content. The Gemini detector using this method achieves a Macro-F1 score of 85.65%, outperforming baseline detectors and surpassing the best traditional detector, RoBERTa.
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.