SOURCE-LINKED INTELLIGENCE

When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a latent-key view of inference, where answer selection depends on competition among associations acquired during pretraining. We show that model predictions can be highly sensitive to individual query keywords, that these influential keywords exhibit entity-specific binding, and that their effects are systematically shaped by pretraining frequency. Multiple bindings can also compete and exhibit higher-order interactions within the same query. Based on

Read original source ↗ Open in workspace

recordType

paper

region

Global