arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2604.26328cs.CLcs.AI
收藏

DSIPA：通过情感不变模式分歧分析检测大语言模型生成文本

DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis

School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）；Shanghai Key Laboratory of Integrated Administration Technologies for Information Security（上海信息安全集成管理技术重点实验室）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）

Siyuan Li, Aodu Wulianghai, Guangyan Li, Xi Lin, Qinghua Mao, Yuliang Chen, Jun Wu, Jianhua Li

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

DSIPA是一种无需训练的框架，通过量化在受控风格变化下的情感分布稳定性，检测大语言模型生成的文本，其在多个领域和对抗条件下均表现出更高的检测准确率和鲁棒性。

摘要：

大语言模型（LLMs）的快速发展带来了新的安全挑战，特别是在检测用于虚假信息、冒充和内容伪造的机器生成文本方面。现有检测方法在对抗扰动、改写攻击和领域转移方面缺乏鲁棒性，通常需要对模型参数的严格访问或大量标记数据。为此，我们提出了DSIPA，一种新的无需训练的框架，通过量化在受控风格变化下的情感分布稳定性来检测LLM生成的内容。基于LLMs通常表现出更一致的情感输出，而人类写作文本则具有更大的情感变化的观察。我们的框架以零样本、黑盒方式运行，利用两个无监督指标，情感分布一致性与情感分布保留，来捕捉这些内在的行为不对称性，而无需参数更新或概率访问。在最先进的专有和开源模型上进行了广泛实验，包括GPT-5.2、Gemini-1.5-pro、Claude-3和LLaMa-3.3。在新闻文章、编程代码、学生作文、学术论文和社区评论等五个领域上的评估表明，DSIPA在基准方法上将F1检测得分提高了高达49.89%。该框架在不同领域和对抗条件下表现出卓越的泛化能力和强抗扰性，为在演变的LLM景观中安全内容识别提供了一种稳健且可解释的行为信号。

英文摘要：

The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misinformation, impersonation, and content forgery. Most existing detection approaches struggle with robustness against adversarial perturbation, paraphrasing attacks, and domain shifts, often requiring restrictive access to model parameters or large labeled datasets. To address this, we propose DSIPA, a novel training-free framework that detects LLM-generated content by quantifying sentiment distributional stability under controlled stylistic variation. It is based on the observation that LLMs typically exhibit more emotionally consistent outputs, while human-written texts display greater affective variation. Our framework operates in a zero-shot, black-box manner, leveraging two unsupervised metrics, sentiment distribution consistency and sentiment distribution preservation, to capture these intrinsic behavioral asymmetries without the need for parameter updates or probability access. Extensive experiments are conducted on state-of-the-art proprietary and open-source models, including GPT-5.2, Gemini-1.5-pro, Claude-3, and LLaMa-3.3. Evaluations on five domains, such as news articles, programming code, student essays, academic papers, and community comments, demonstrate that DSIPA improves F1 detection scores by up to 49.89% over baseline methods. The framework exhibits superior generalizability across domains and strong resilience to adversarial conditions, providing a robust and interpretable behavioral signal for secure content identification in the evolving LLM landscape.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑