paper-with-me

홈 › Papers

EnsemJudge: Enhancing Reliability in Chinese LLM-Generated Text Detection through Diverse Model Ensembles

2026-03-30 · Zhuoshang Wang, Yubing Ren, Guoyu Zhao, Xiaowei Zhu, Hao Li, Yanan Cao arxiv

Large Language Models (LLMs) are widely applied across various domains due to their powerful text generation capabilities. While LLM-generated texts often resemble human-written ones, their misuse can lead to significant societal risks. Detecting such texts is an essential technique for mitigating LLM misuse, and many detection methods have shown promising results across different datasets. However, real-world scenarios often involve out-of-domain inputs or adversarial samples, which can affect the performance of detection methods to varying degrees. Furthermore, most existing research has focused on English texts, with limited work addressing Chinese text detection. In this study, we propose EnsemJudge, a robust framework for detecting Chinese LLM-generated text by incorporating tailored strategies and ensemble voting mechanisms. We trained and evaluated our system on a carefully constructed Chinese dataset provided by NLPCC2025 Shared Task 1. Our approach outperformed all baseline methods and achieved first place in the task, demonstrating its effectiveness and reliability in Chinese LLM-generated text detection. Our code is available at https://github.com/johnsonwangzs/MGT-Mini.

📄 PDF Abstract BibTeX arXiv:2603.27949

Code (0)

등록된 구현이 없습니다.

Tasks

Text GenerationText Detection

Similar Papers 제목 키워드 기반

CEC-Zero: Chinese Error Correction Solution Based on LLM

2025-05-14 · Sophie Zhang, Zhiming Lin

Recent advancements in large language models (LLMs) demonstrate exceptional Chinese text processing capabilities, particularly in Chinese Spelling Correction (CSC). While LLMs outperform traditional BERT-based models in …

Domain GeneralizationReinforcement Learning (RL)Spelling Correction

MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs

2025-10-27 · Yucheng Ning, Xixun Lin, Fang Fang, Yanan Cao arxiv

The widespread adoption of Large Language Models (LLMs) raises critical concerns about the factual accuracy of their outputs, especially in high-risk domains such as biomedicine, law, and education. Existing evaluation m…

Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry

2025-09-01 · Shanshan Wang, Junchao Wu, Fengying Ye, Jingming Yao 외 arxiv

The rapid development of advanced large language models (LLMs) has made AI-generated text indistinguishable from human-written text. Previous work on detecting AI-generated text has made effective progress, but has not i…

Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT

2024-06-13 · Zhen Tao, Yanfang Chen, Dinghao Xi, Zhiyu Li 외

The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored …

BenchmarkingLLM-generated Text DetectionQuestion AnsweringText Detection+1

Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry

2026-04-11 · Jiang Li, Tian Lan, Shanshan Wang, Dongxing Zhang 외 arxiv

The rapid development of large language models (LLMs) has extended text generation tasks into the literary domain. However, AI-generated literary creations has raised increasingly prominent issues of creative authenticit…

Text Generation