Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model

ArXi:2604.21223v1 Announce Type: new Large language models (LLMs) have nstrated remarkable capabilities across various tasks. However, their ability to generate human-like text has raised concerns about potential misuse. This underscores the need for reliable and effective methods to detect LLM-generated text. In this paper, we propose IRM, a novel zero-shot approach that leverages Implicit Reward Models for LLM-generated text detection. Such implicit reward models can be derived from publicly available instruction-tuned and base models.