Study Challenges Unique Hallucination Neurons
A new preprint found small neuron sets that predict incorrect answers, but the selected units were unstable and often interchangeable with correlated features. Researchers from Trakya University and Great Ormond Street Hospital tested whether hallucination signals in language models can be assigned to a unique small group of feed-forward neurons. Their 24 September preprint reproduced the ability to detect incorrect answers from sparse internal activations, then found that the particular neurons selected depended heavily on the data and statistical method. ...