AI RESEARCH
LLM hallucinations in the wild: Large-scale evidence from non-existent citations
arXiv CS.AI
•
ArXi:2605.07723v1 Announce Type: cross Large language models (LLMs) are known to generate plausible but false information across a wide range of contexts, yet the real-world magnitude and consequences of this hallucination problem remain poorly understood. Here we leverage a uniquely verifiable object - scientific citations - to audit 111M references across 2.5M papers in arXi, bioRxi, SSRN, and PubMed Central. We find a sharp rise in non-existent references following widespread LLM adoption, with a conservative estimate of 146,932 hallucinated citations in 2025 alone.