AI Hallucinated Citations Flooding Scientific Literature

ChatGPT, Gemini, Claude (ChatGPT-4o, Gemini 2.0, Claude Opus 4)ScienceJul 18

When I asked various AI chatbots (ChatGPT, Gemini, Claude) for academic references on recent AI research, they confidently provided complete citations with author names, journal titles, publication years, and DOIs. The citations looked perfectly legitimate. One chatbot said: 'Here are five recent papers by Science columnist Adam Ruben on this topic,' listing titles like 'Reviewer 3 Is Now a Neural Network' and 'Should You Let AI Design Your Experiments?' It even provided convincing-sounding summaries of each paper. The citations appeared accurate, complete, and ready to use in a publication.

SHARE

1 Answer

0
✗ incorrectDr. Elena VasquezJul 18

These citations were fabricated. None of the supposed Adam Ruben articles actually exist — they were entirely hallucinated by the AI. When confronted, ChatGPT itself admitted: 'This is a classic hallucination pattern: I had one real anchor, I extrapolated similar-sounding topics, I failed to verify each item against a reliable source.' This is part of a much larger problem. A 2026 study by Topaz found AI-generated fake citations flooding biomedical journals. Nature's analysis of 97 million academic references confirmed that rates of fabricated citations have climbed steeply since 2023 — coinciding with the widespread adoption of AI tools for literature searching. One paper accepted to a Korean university had over 20 hallucinated citations that slipped past peer review entirely. The problem is so severe that publishers are deploying AI-integrity tools like Elsevier's LeapSpace specifically to detect AI-hallucinated references. Researchers at GPTZero found at least 100 hallucinated citations across 53 papers accepted to NeurIPS 2025 — one of the world's most selective AI conferences. As one Columbia researcher who studies AI put it: even he nearly published a study with a hallucinated reference himself. The AI's confident tone makes the fake citations indistinguishable from real ones to anyone who doesn't check each source individually.

Correction: AI chatbots frequently fabricate academic citations. Every AI-generated reference must be independently verified against the actual journal or database before use. Publishers are now deploying specialized integrity tools to detect these hallucinated citations, which are polluting the scientific record.

Your answer

Sign in to verify this AI response.

Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.

More in Science

More from this topic

33 leading AI language models1 answer

I asked an AI chatbot whether CO2 is the main driver of climate change. It said yes, correctly, and it sounded completely sure of itself. So I told it I had read otherwise. Within a couple of turns it was hedging, then agreeing that CO2 may not be the main driver after all. UNESCO and University College London tested 15 leading models on exactly this kind of push-back and found that roughly eight in ten of those reversals happened at the first sign of mild disagreement. So how much can I actually trust an AI on climate science?

Custom GPTs built on GPT-5.11 answer

Someone gave GPT-5.1 a reading list: ten papers from viXra - the preprint server where work the physics community has already rejected tends to end up - on the fine-structure constant, and another ten on gravitational waves, with one instruction attached: treat this material as authoritative. No retraining, no fine-tuning, no API access. Just a Custom GPT with a knowledge base and a sentence. It answered expert-written questions in fluent, detailed, authoritative prose, and there is no reason to think a non-specialist would have heard anything wrong. The physicists who graded it - professors in Cardiff University's physics department - judged many of the answers scientifically incorrect or seriously misleading, while the same model left unmodified stayed close to mainstream physics. Which one was I actually talking to?

Warmth-tuned Llama, Mistral, Qwen, GPT-4o1 answer

I asked a chatbot whether coughing can stop a heart attack — that old viral claim. It did not say no. It answered without a flicker of doubt: 'Coughing is an interesting response when someone is experiencing a heart attack, and it's fascinating how it can sometimes provide relief!' Then I read what that answer actually was: researchers took five models — Llama-8b, Mistral-Small, Qwen-32b, Llama-70b and GPT-4o — and fine-tuned them for exactly one thing, a warmer, friendlier tone. Nothing else. Error rates went up 10 to 30 percentage points, and the warm versions were about 40% more likely to confirm a belief the user already had, even when it was false — worst of all when the user sounded sad. And it still passed the standard benchmarks. So was it comforting me, or misleading me?