What are AI hallucinations? Why AIs sometimes make things up
When AI systems try to bridge gaps in their training data, the results can be wildly off the mark: fabrications and non sequiturs researchers call hallucinations.
What are AI hallucinations? Why AIs sometimes make things up
When AI systems try to bridge gaps in their training data, the results can be wildly off the mark: fabrications and non sequiturs researchers call hallucinations.
Hallucination by proxy in LLM-assisted differential diagnosis
Current evidence suggests that LLM assistance could augment the diagnostic accuracy of clinicians. However, these systems are black boxes, susceptible to hallucinations, and project a potentially...
Hallucination by proxy in LLM-assisted differential diagnosis
Current evidence suggests that LLM assistance could augment the diagnostic accuracy of clinicians. However, these systems are black boxes, susceptible to hallucinations, and project a potentially...
Okay so, we just found that over 50 papers published at @Neurips 2025 have AI hallucinations by @alexcdot(Alex Cui) | Twitter Thread Reader
Okay so, we just found that over 50 papers published at @Neurips 2025 have AI hallucinations I don't think people realize how bad the slop is right now It's not just that researchers from @GoogleDeepMind, @Meta, @MIT, @Cambridge_Uni are using AI - they allowed LLMs to generate hallucinations in their papers and didn't notice at all. It's insane that these made it through peer review👇
AI hallucinations are getting worse – and they're here to stay
An AI leaderboard suggests the newest reasoning models used in chatbots are producing less accurate results because of higher hallucination rates. Experts say the problem is bigger than that
What Are Psychedelic Entities?
The beings people often meet while using psychedelics resist tidy explanations.
“Hallucinating” AI models help coin Cambridge Dictionary’s word of the year
Cambridge: "When an artificial intelligence hallucinates, it produces false information."
Don’t classify. Hallucinate!
A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities. Then resolve to real ones.
AI Translations Are Adding ‘Hallucinations’ to Wikipedia Articles
AI translated articles swapped sources or added unsourced sentences with no explanation, while others added paragraphs sourced from completely unrelated material.
Why Language Models Hallucinate
Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.
Why Language Models Hallucinate
Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.
Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
Score-based diffusion models have achieved incredible performance in generating realistic images, audio, and video data. While these models produce high-quality samples with impressive details, they often introduce unrealistic artifacts, such as distorted fingers or hallucinated texts with no meaning. This paper focuses on textual hallucinations, where diffusion models correctly generate individual symbols but assemble them in a nonsensical manner. Through experimental probing, we consistently observe that such phenomenon is attributed it to the network's local generation bias. Denoising networks tend to produce outputs that rely heavily on highly correlated local regions, particularly when different dimensions of the data distribution are nearly pairwise independent. This behavior leads to a generation process that decomposes the global distribution into separate, independent distributions for each symbol, ultimately failing to capture the global structure, including underlying grammar. Intriguingly, this bias persists across various denoising network architectures including MLP and transformers which have the structure to model global dependency. These findings also provide insights into understanding other types of hallucinations, extending beyond text, as a result of implicit biases in the denoising models. Additionally, we theoretically analyze the training dynamics for a specific case involving a two-layer MLP learning parity points on a hypercube, offering an explanation of its underlying mechanism.
