Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
Runheng Liu, Heyan Huang, Xingchen Xiao, Zhijing Wu
Abstract
Large language models (LLMs) have demonstrated 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. Previous reward-based method relies on preference construction and task-specific fine-tuning. In comparison, IRM requires neither preference collection nor additional training. We evaluate IRM on the DetectRL benchmark and demonstrate that IRM can achieve superior detection performance, outperforms existing zero-shot and supervised methods in LLM-generated text detection.
BibTeX
@inproceedings{
liu2025zeroshot,
title={Zero-Shot Detection of {LLM}-Generated Text via Implicit Reward Model},
author={Runheng Liu and Heyan Huang and Xingchen Xiao and Zhijing Wu},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=2VdsYVXLDl}
}