LLM Paternity Test: Generated Text Detection with LLM Genetic Inheritance

arXiv:2305.12519v2 Announce Type: replace-cross
Abstract: Large language models (LLMs) can generate texts that carry the risk of various misuses, including plagiarism, planting fake reviews on e-commerce platforms, or creating inflammatory false tweets. Detecting whether a text is machine-generated has thus become increasingly important. While existing detection methods exhibit superior performance, they often lack generalizability due to their heavy dependence on training data. To alleviate this problem, we propose a model-related generated text detection method, the LLM Paternity Test (LLM-Pat). Specifically, …

abstract arxiv become commerce cs.ai cs.cl cs.lg detection detection methods e-commerce e-commerce platforms fake false generate generated inheritance language language models large language large language models llm llms machine performance plagiarism platforms reviews risk test text tweets type