Leveraging Knowledge Graphs and LLMs for Structured Generation of Misinformation
This work addresses the societal threat of misinformation by enabling structured generation for proactive assessment, though it is incremental as it builds on existing knowledge graph and LLM techniques.
The paper tackled the problem of misinformation generation by proposing a method that uses knowledge graphs to systematically create fake triplets and guide large language models in producing misinformation, resulting in statements that are challenging for humans to detect, as demonstrated with publicly available datasets like WikiGraphs.
The rapid spread of misinformation, further amplified by recent advances in generative AI, poses significant threats to society, impacting public opinion, democratic stability, and national security. Understanding and proactively assessing these threats requires exploring methodologies that enable structured and scalable misinformation generation. In this paper, we propose a novel approach that leverages knowledge graphs (KGs) as structured semantic resources to systematically generate fake triplets. By analyzing the structural properties of KGs, such as the distance between entities and their predicates, we identify plausibly false relationships. These triplets are then used to guide large language models (LLMs) in generating misinformation statements with varying degrees of credibility. By utilizing structured semantic relationships, our deterministic approach produces misinformation inherently challenging for humans to detect, drawing exclusively upon publicly available KGs (e.g., WikiGraphs). Additionally, we investigate the effectiveness of LLMs in distinguishing between genuine and artificially generated misinformation. Our analysis highlights significant limitations in current LLM-based detection methods, underscoring the necessity for enhanced detection strategies and a deeper exploration of inherent biases in generative models.