SENTRA: A General Purpose Encoder for LLM Text Detection

ACL ARR 2025 February Submission4981 Authors

Abstract: LLMs are becoming increasingly capable and widespread. Consequently, the potential and reality of their misuse is also growing. In this work, we address the problem of detecting LLM-generated text that is not explicitly declared as such. We present a novel, general-purpose, and supervised LLM text detector, SElected-Next-Token tRAnsformer (SENTRA). SENTRA is a Transformer-based encoder leveraging selected-next-token-probability sequences and utilizing contrastive pre-training on large amounts of unlabeled data. Our experiments on three popular public datasets across 24 domains of text demonstrate SENTRA is a general-purpose classifier that significantly outperforms several popular baselines in the out-of-domain setting.

Paper Type: Long

Research Area: Special Theme (conference specific)

Research Area Keywords: generalization, contrastive learning, rumor/misinformation detection, LLM text detection

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 4981