Language models have achieved remarkable performance on a wide range of tasks
that require natural language understanding. Nevertheless, state-of-the-art
models have generally struggled with tasks that require quantitative reasoning,
such as solving mathematics, science, and engineering problems at the college
level. To help close this gap, we introduce Minerva, a large language model
pretrained on general natural language data and further trained on technical
content. The model achieves state-of-the-art performance on technical
benchmarks without the use of external tools. We also evaluate our model on
over two hundred undergraduate-level problems in physics, biology, chemistry,
economics, and other sciences that require quantitative reasoning, and find
that the model can correctly answer nearly a third of them.

Minerva 是一个预训练于自然语言数据并进一步训练于技术内容的大型语言模型，通过在技术基准测试中达到最先进的性能，帮助解决了需要量化推理的数学、科学和工程问题的任务，同时在 200 多个需要量化推理的本科水平的物理学、生物学、化学、经济学和其他科学问题上能够正确回答近三分之一的问题。

使用语言模型解决定量推理问题

Solving Quantitative Reasoning Problems with Language Models

Knowledge bases (KB), both automatically and manually constructed, are often
incomplete --- many valid facts can be inferred from the KB by synthesizing
existing information. A popular approach to KB completion is to infer new
relations by combinatory reasoning over the information found along other paths
connecting a pair of entities. Given the enormous size of KBs and the
exponential number of paths, previous path-based models have considered only
the problem of predicting a missing relation given two entities or evaluating
the truth of a proposed triple. Additionally, these methods have traditionally
used random paths between fixed entity pairs or more recently learned to pick
paths between them. We propose a new algorithm MINERVA, which addresses the
much more difficult and practical task of answering questions where the
relation is known, but only one entity. Since random walks are impractical in a
setting with combinatorially many destinations from a start node, we present a
neural reinforcement learning approach which learns how to navigate the graph
conditioned on the input query to find predictive paths. Empirically, this
approach obtains state-of-the-art results on several datasets, significantly
outperforming prior methods.

提出了一种名为 MINERVA 的算法，采用神经强化学习方法解决在只知道一个实体的情况下，找到预测路径的困难问题，以实现知识库（KB）的完善，这种方法在多个数据集上均取得了最新成果。