It's no secret that large language models (LLMs) like the ones that power popular chatbots like ChatGPT are far from infallible. They have a nagging and ever-presnt tendency to contort the truth with an unnerving degree of confidence. And when it comes to medical data, those kinds of discrepancies become a whole lot more serious. Researchers at New York University have found that if a mere 0.001 percent of the training data of a given LLM is "poisoned," or deliberately planted with misinformation, the entire training set is likely to propagate errors. As detailed in a paper published in […]