Topic
hallucinations
New Method LUCID Detects Hallucinations in LLM-Based Knowledge Graph Reasoning
Researchers introduce LUCID, the first hallucination detection method designed for large language model-based knowledge graph reasoning. By jointly leveraging attention scores, KG semantics, and structural information via a graph neural network, LUCID achieves state-of-the-art performance across nine datasets compared to 15 baselines. The method addresses a critical gap where existing detection techniques overlook structural information in knowledge graphs.
New Orthogonal Projection Method Reduces Hallucinations in Vision-Language AI Explanations
Researchers propose Orthogonal Semantic Projection (OSP), a geometric intervention that reduces semantic hallucination in Vision-Language Model explanations. The method orthogonalizes query vectors against distractor concepts, improving attribution fidelity for safety-critical AI applications.
Technology KPMG Report on AI Found Riddled with AI-Generated False Citations
A KPMG report on agentic AI was found to contain pervasive AI hallucinations, with GPTZero investigators revealing that only five of 45 citations accurately pointed to real sources. The phenomenon, termed 'vibe citing', underscores the risk of misinformation spreading through influential reports.