---
title: "VaryBalance: Detecting LLM-Generated Text Through Variation"
authors:
  - "Xuecong Li"
  - "Xiaohong Li"
  - "Qiang Hu"
  - "Yao Zhang"
  - "Junjie Wang"
doi: "10.24963/ijcai.2026/648"
url: "https://ijcai.org/proceedings/2026/648"
pdf: "https://ijcai.org/proceedings/2026/0648.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5819-5827"
track: "Main Track"
keywords:
  - "Natural Language Processing: Language models"
  - "Natural Language Processing: Text classification"
  - "Natural Language Processing: Interpretability and analysis of models for NLP"
---

# VaryBalance: Detecting LLM-Generated Text Through Variation

Xuecong Li, Xiaohong Li, Qiang Hu, Yao Zhang, Junjie Wang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5819-5827. DOI: [10.24963/ijcai.2026/648](https://doi.org/10.24963/ijcai.2026/648)

## Abstract

Detecting text generated by large language models~(LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rely on text-level features, leading to imprecise detection ability. In this paper, we propose a simple but effective and practical LLM-generated text detection method, VaryBalance. The core of VaryBalance is that, compared to LLM-generated texts, there is a greater difference between human texts and their rewritten version via LLMs. Leveraging this observation, VaryBalance quantifies this through mean standard deviation and distinguishes human texts and LLM-generated texts. Comprehensive experiments demonstrated that VaryBalance outperforms the state-of-the-art detectors, i.e., Binoculars, by up to 34.3% in terms of AUROC, and maintains robustness against multiple generating models and languages.