RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
This work addresses the need for robust detection of LLM-generated content to prevent misuse, though it appears incremental as it builds on existing detection methods by focusing on internal representations.
The paper tackles the problem of detecting LLM-generated text by hypothesizing that internal representations of LLMs contain more effective features for distinguishing such text from human-written text, and it proposes RepreGuard, which achieves an average 94.92% AUROC in both in-distribution and out-of-distribution scenarios.
Detecting content generated by large language models (LLMs) is crucial for preventing misuse and building trustworthy AI systems. Although existing detection methods perform well, their robustness in out-of-distribution (OOD) scenarios is still lacking. In this paper, we hypothesize that, compared to features used by existing detection methods, the internal representations of LLMs contain more comprehensive and raw features that can more effectively capture and distinguish the statistical pattern differences between LLM-generated texts (LGT) and human-written texts (HWT). We validated this hypothesis across different LLMs and observed significant differences in neural activation patterns when processing these two types of texts. Based on this, we propose RepreGuard, an efficient statistics-based detection method. Specifically, we first employ a surrogate model to collect representation of LGT and HWT, and extract the distinct activation feature that can better identify LGT. We can classify the text by calculating the projection score of the text representations along this feature direction and comparing with a precomputed threshold. Experimental results show that RepreGuard outperforms all baselines with average 94.92% AUROC on both in-distribution (ID) and OOD scenarios, while also demonstrating robust resilience to various text sizes and mainstream attacks. Data and code are publicly available at: https://github.com/NLP2CT/RepreGuard