# LLM hallucinations in the wild: Large-scale evidence from non-existent citations

arXiv: https://arxiv.org/abs/2605.07723 · HTML: https://mlsanity.com/paper/2605.07723/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 10 of 10)

- [Scientific production in the era of Large Language Models](https://mlsanity.com/paper/2601.13187/) (2026)
- [HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences](https://mlsanity.com/paper/2601.18724/) (2026)
- [Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis](https://mlsanity.com/paper/2309.05217/) (2023)
- [FLAWS: A Benchmark for Error Identification and Localization in Scientific Papers](https://mlsanity.com/paper/2511.21843/) (2025)
- [Exploring the use of AI authors and reviewers at Agents4Science](https://mlsanity.com/paper/2511.15534/) (2025)
- [Academic journals' AI policies fail to curb the surge in AI-assisted academic writing](https://mlsanity.com/paper/2512.06705/) (2025)
- [BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature](https://mlsanity.com/paper/2601.16993/) (2026)
- [Where there's a will there's a way: ChatGPT is used more for science in countries where it is prohibited](https://mlsanity.com/paper/2406.11583/) (2024)
- [FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG](https://mlsanity.com/paper/2601.05866/) (2026)
- [To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis](https://mlsanity.com/paper/2512.05925/) (2025)

## Built on by (most cited first, 7 of 7)

- [Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud](https://mlsanity.com/paper/2607.10712/) (2026)
- [Most biomedical publications show signs of LLM-assisted writing](https://mlsanity.com/paper/2608.10715/) (2026)
- [AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions](https://mlsanity.com/paper/2606.22859/) (2026)
- [Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences](https://mlsanity.com/paper/2607.00738/) (2026)
- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [Scientific exploration, collaboration and labor division in the large language model era](https://mlsanity.com/paper/2607.20923/) (2026)
- [Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation](https://mlsanity.com/paper/2609.01432/) (2026)

## Abstract (arXiv)

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 111 million references across 2.5 million papers in arXiv, bioRxiv, 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. These errors are diffusely embedded across many papers but especially pronounced in fields with rapid AI uptake, in manuscripts with linguistic signatures of AI-assisted writing, and among small and early-career author teams. At the same time, hallucinated references disproportionately assign credit to already prominent and male scholars, suggesting that LLM-generated errors may reinforce existing inequities in scientific recognition. Preprint moderation and journal publication processes capture only a fraction of these errors, suggesting that the spread of hallucinated content has outpaced existing safeguards. Together, these findings demonstrate that LLM hallucinations are infiltrating knowledge production at scale, threatening both the reliability and equity of future scientific discovery as human and AI systems draw on the existing literature.