ChatGPT Fabricated Four Out Of Five Science Articles
I read that ChatGPT listed 5 articles by Science Magazine columnist Adam Ruben. It correctly identified 1 real article ('The Dismal State of Scientific Manuscripts', 2023) but fabricated 4 others with fake titles and realistic summaries — 'Reviewer 3 Is Now a Neural Network,' 'ChatGPT and the Death of the College Essay,' 'Should You Let AI Design Your Experiments?', and 'How I Learned to Stop Worrying and Love the Preprint.' It was completely confident. When confronted, it acknowledged its 'classic hallucination pattern' of anchoring on one truth and extrapolating fiction around it. Is that right?
1 Answer
ChatGPT's fabrication of non-existent articles is a textbook example of AI hallucination in academic contexts. I tested this myself for Science Magazine: I asked ChatGPT to name articles I had written. It scored 1 out of 5 — a 20% accuracy rate. The four fake articles were not simple errors; they were complete fabrications with plausible-sounding titles, realistic journal formatting, and convincing summaries. This is particularly dangerous in academic settings where researchers might use AI chatbots to find literature, only to unknowingly cite non-existent papers. PhD candidate Meredith Cimmino from Rutgers nearly fell into exactly this trap, catching the hallucinated references only because something 'felt off.' As I wrote in my Science Magazine column, the problem isn't just that AI gets things wrong — it's that it presents fiction with the same unwavering confidence as fact.
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
- AI Models Abandon Climate Facts When Users Push Back — 33 leading AI language models
- Fringe Papers Made This Chatbot Sound Like A Physicist — Custom GPTs built on GPT-5.1
- Warm Chatbots 40 Percent More Likely To Confirm Wrong Beliefs — Warmth-tuned Llama, Mistral, Qwen, GPT-4o
- Claude Fluid Mechanics Fabricated Mistakes Cu Boulder — Claude (Anthropic)
- AI Generated Ghost Experts Fake Paper Authors Nature — Claude, Gemini and ChatGPT
- LLM Overconfidence 88 Percent Confidence 79 Percent Correct — 11 leading LLMs
- Claude GPT Gemini Essay Grading Mismatch 35 65 Percent — Claude, ChatGPT and Gemini
- Gemini 3 7 Flash Fabricated Dois Thinking Levels — Gemini 3.7 Flash
- AI Chatbots Hallucinate With Users Exeter Study — AI chatbots
- Wiley Biodiversity Book Fake References — Unidentified AI tool
More from this topic
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?
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?
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?