Analogical proportions compare pairs of items (a, b) and (c, d) in terms of their differences and similarities. They play a key role in the formalization of analogical inference. The paper first discusses how to improve analogical inference in terms of accuracy and in terms of computational cost. Then it indicates the potential of analogical proportions for explanation. Finally, it highlights the close relationship between analogical proportions and multi-valued dependencies, which reveals an unsuspected aspect of the former.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
我们解决了几个射击开放式识别（FSOSR）问题，即在我们只有很少的标签样本的一组类中分类的实例，同时检测不属于任何已知类别的实例。偏离现有文献，我们专注于开发模型不足的推理方法，这些方法可以插入任何现有模型，无论其架构或培训程序如何。通过评估嵌入的各种模型的质量，我们量化了模型 - 敏捷FSOSR的内在难度。此外，公平的经验评估表明，在FSOSR的电感环境中，KNN检测器和原型分类器的天真组合在专业或复杂方法之前。这些观察结果促使我们诉诸于转导，这是对标准的几次学习问题的流行而实用的放松。我们介绍了一个开放的设置转导信息最大化方法OSTIM，该方法幻觉了异常原型，同时最大程度地提高了提取的特征和作业之间的相互信息。通过跨越5个数据集的广泛实验，我们表明OSTIM在检测开放式实例的同时，在与最强的托管方法竞争时，在检测开放式实例时都超过了电感和现有的转导方法。我们进一步表明，OSTIM的模型不可知论使其能够成功利用最新体系结构和培训策略的强大表现能力而没有任何超参数修改，这是一个有希望的信号，即将来临的建筑进步将继续积极影响Ostim的表现。
translated by 谷歌翻译