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 2406.17992cs.CLcs.AI
收藏

捕捉变色龙:检测利用大型语言模型生成的不断演变的虚假信息

Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Models

School of Computing and Augmented Intelligence(计算与增强智能学院);Arizona State University(亚利桑那州立大学)

Bohan Jiang, Chengshuai Zhao, Zhen Tan, Huan Liu

AI总结:

针对LLM生成虚假信息不断演变的问题,提出参数高效的DELD方法,联合PLM事实核查能力与各LLM生成特性,顺序拼接知识,显著优于现有方法。

摘要:

尽管近期在检测大型语言模型(LLM)生成的虚假信息方面取得了进展,但当前的研究工作忽视了这类虚假信息不断演变的特性。在本工作中,我们研究了一个具有挑战性且实用的研究问题:检测不断演变的LLM生成虚假信息。虚假信息随着LLM及其变体的快速发展而不断演变。因此,检测模型面临重大挑战。首先,为每个虚假信息生成器分别训练模型是低效的。其次,在按顺序遇到不断演变的LLM生成虚假信息时,检测性能会下降。为解决此问题,我们提出了DELD(检测不断演变的LLM生成虚假信息),一种参数高效的方法,该方法联合利用预训练语言模型(PLM)的通用事实核查能力以及各种LLM的独立虚假信息生成特性。具体而言,学习到的特性被顺序拼接以促进知识积累与转化。DELD通过将虚假信息的语义嵌入与可训练的软提示相结合来引发模型特定知识,从而解决标签稀缺问题。我们的实验表明,DELD显著优于最先进的方法。此外,我们的方法提供了对不同LLM生成虚假信息独特模式的关键见解,为这一研究方向提供了有价值的视角。

英文摘要:

Despite recent advancements in detecting disinformation generated by large language models (LLMs), current efforts overlook the ever-evolving nature of this disinformation. In this work, we investigate a challenging yet practical research problem of detecting evolving LLM-generated disinformation. Disinformation evolves constantly through the rapid development of LLMs and their variants. As a consequence, the detection model faces significant challenges. First, it is inefficient to train separate models for each disinformation generator. Second, the performance decreases in scenarios when evolving LLM-generated disinformation is encountered in sequential order. To address this problem, we propose DELD (Detecting Evolving LLM-generated Disinformation), a parameter-efficient approach that jointly leverages the general fact-checking capabilities of pre-trained language models (PLM) and the independent disinformation generation characteristics of various LLMs. In particular, the learned characteristics are concatenated sequentially to facilitate knowledge accumulation and transformation. DELD addresses the issue of label scarcity by integrating the semantic embeddings of disinformation with trainable soft prompts to elicit model-specific knowledge. Our experiments show that \textit{DELD} significantly outperforms state-of-the-art methods. Moreover, our method provides critical insights into the unique patterns of disinformation generation across different LLMs, offering valuable perspectives in this line of research.

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。

↑