基于多信号融合的中文伪文本检测系统，精准区分人工、大模型生成与润色文本。
EVIL-Detect for NLPCC 2026 Shared Task 6: LLM-Generated Text Detection
- 融合编辑程度回归、零样本似然对比等多信号，增强判别能力。
- 在真实场景下实现0.8888的宏平均F1，排名榜首。
- 适合需要高鲁棒性中文伪文本检测的落地应用。
大型语言模型的快速发展加剧了对可靠生成文本检测的需求，尤其在包含人工写作文本（HWT）、大模型生成文本（LGT）和大模型润色文本（HLT）的真实中文场景中。本文提出EVIL-Detect，一种具备冲突感知融合能力的多信号集成框架，用于NLPCC 2026共享任务6。该系统整合了编辑程度回归、零样本似然对比信号、词汇统计特征与保守文本规则，通过校准决策边界与冲突感知融合机制，在强分布外迁移条件下显著提升鲁棒性，官方评测中达到0.8888的宏平均F1，排名第一。代码已开源：https://github.com/bbbbhrrrr/evildetect。
原文摘要 · Abstract (English)
The rapid development of large language models (LLMs) has increased the need for reliable detection of LLM-generated text, especially in realistic Chinese scenarios involving human-written text (HWT), LLM-generated text (LGT), and LLM-refined text (HLT). This paper presents EVIL-Detect, a multi-signal ensemble framework with conflict-aware fusion for NLPCC 2026 Shared Task 6. The system integrates edit-extent regression, zero-shot likelihood-contrast signals, lexical statistics, and conservative text rules. With calibrated decision boundaries and conflict-aware integration, our system improves robustness under strong out-of-distribution shifts, achieving a macro-F1 score of 0.8888 and ranking first in the official evaluation. Our code is available at https://github.com/bbbbhrrrr/evildetect.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。