Sep 2026· Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence· 0 citations· 31 references
TL;DR
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, and quantifies this through Mean Squared Deviation and distinguishes human texts and LLM-generated texts.
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.
It is shown that the strength of this signal depends on text length and sampling range: spectral evidence is clearest for long, continuous, constrained generation, while short, fragmented, mixed, and edited settings require complementary confidence and fluctuation views.
Haitong Luo, Xuying Meng, Wei-Yao Zhang et al.· 1 citation
The key idea is to smooth adjacent token scores to reduce their variability, while using an adaptive Lepski-type rule to select the bandwidth according to the local authorship structure, and the proposed method achieves favorable mean square error performance in estimating the underlying signal.
Yangjun Lu, Hongyi Zhou, F. Spill et al.· arXiv.org· 0 citations
Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge. While LLMs are trained to write like humans, we hypothesize that this training leaves an indelible mark. LLMs develop a particularly strong aversion to token repetition very early in training. This bias pe...
A novel method named IED is proposed, which leverages the information gain to construct the vector of which each dimension represents the information entropy of each word, and then adopts a classifier to conduct the detection.
Xiao-Quan Yi, Hao-Zhao Wang, Jing-Cai Guo· Proceedings of the Thirty-Fi...· 0 citations
A novel paradigm called Human vs. LLM Identification (HLI) is proposed which introduces a Retrieval-Augmented Generation (RAG)-inspired evidence-based detection strategy alongside a fine-tuned transformer classifier.
Ibtasam Ur Rehman, Muhammad Islam, Muhammad Yousaf Rehman et al.· Knowledge· 0 citations
EVIL-Detect, a multi-signal ensemble framework with conflict-aware fusion for NLPCC 2026 Shared Task 6, improves robustness under strong out-of-distribution shifts, achieving a macro-F1 score of 0.8888 and ranking first in the official evaluation.
Hong-Rui Bao, Hangyu Rong, Zhuo Wang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
