According to a new study, many AI models don't answer accurately about world history which is a very concerning matter. The ...
解难题如探囊取物,答历史却步履维艰。在人工智能交出的“成绩单”上,历史学成了一门“短板学科”。奥地利复杂性科学中心(CSH)最新研究显示,即便是最先进的GPT-4 Turbo,在博士级历史知识测试中也仅获得46%的准确率,虽然超过25%的“蒙题”水平,但距离“及格”仍有不小差距。相关研究成果近日在加拿大温哥华举行的神经信息处理系统会议(NeurIPS)上发布。