Detecting AI-Generated Texts in Cross-Domains

TL;DR

A ranking classifier called RoBERTa-Ranker, a modified version of RoBERTa, is trained as a baseline model using a dataset that includes a wider variety of texts written by humans and generated by various LLMs, and a method to fine-tune RoBERTa-Ranker that requires only a small amount of labeled data in a new domain.

Abstract

Existing tools to detect text generated by a large language model (LLM) have met with certain success, but their performance can drop when dealing with texts in new domains. To tackle this issue, we train a ranking classifier called RoBERTa-Ranker, a modified version of RoBERTa, as a baseline model using a dataset we constructed that includes a wider variety of texts written by humans and generated by various LLMs. We then present a method to fine-tune RoBERTa-Ranker that requires only a small amount of labeled data in a new domain. Experiments show that this fine-tuned domain-aware model outperforms the popular DetectGPT and GPTZero on both in-domain and cross-domain texts, where AI-generated texts may either be in a different domain or generated by a different LLM not used to generate the training datasets. This approach makes it feasible and economical to build a single system to detect AI-generated texts across various domains.

Figures (2)

• Figure 1: ROC curves for the H-LLM ratio
• Figure 2: F1 scores on datasets of different sizes