AI驱动的生成式因果测试：将脑预测黑箱转化为可验证理论
原标题：Understanding the brain with AI-driven explanations and experiments
AI 摘要
微软研究院与加州大学伯克利分校、旧金山分校及哥伦比亚大学合作，在《自然·神经科学》发表论文，提出生成式因果测试（GCT）框架，将基于大语言模型的脑预测模型转化为可读的简短解释，并通过生成新故事进行因果验证。实验确认了已知脑区选择性，区分了邻近的场所处理区域，并发现了前额叶中针对对话、时间和测量等特定概念的微区域。该方法有望解决神经科学及其他领域黑箱模型的可解释性问题。
正文节选
At a glance - LLM-based models can predict the human brain’s responses to language with high accuracy. But what drives that performance is essentially unreadable: a vast collection of learned parameters, not scientific theories anyone can read. - Generative causal testing (GCT), developed in a collaboration between Microsoft Research, the University of California, Berkeley, the University of California, San Francisco, and Columbia University, distills these brain-prediction models into short ver