推荐nl · 2022-12
“I'd encourage you to read the Minerva paper[4] and update your understanding on what large neural networks are doing.”
推荐读 Minerva 论文,借此更新对大型神经网络能力的认识
Minerva:在技术文本上继续训练,大模型能解大学水平数理题
介绍 Minerva:在通用自然语言数据上预训练、再用技术内容继续训练的大语言模型,不借助外部工具就在技术类基准上达到当时最优。作者还在 200 多道本科水平的物理、生物、化学、经济等定量推理题上评测,模型约能答对近三分之一。
HN 上的人用它作为证据,说明大型神经网络在数学推理上的能力超出人们的预期,并讨论记忆化与数据过滤的影响。
“I'd encourage you to read the Minerva paper[4] and update your understanding on what large neural networks are doing.”
“Minvera scored 65%; the 2021 national average was 57%. See [LINK] and Section 3 of the Minerva paper at Solving Quantitative Reasoning Problems with Language Models”
“Minerva improved it by 50% and PaLM improved it even more.”
“The paper explicitly investigates whether memorization has overly impacted performance.”
“[2] [OTHER_PAPER] and Solving Quantitative Reasoning Problems with Language Models”