Playgrounds for Abstraction and Reasoning
Playgrounds for Abstraction and Reasoning
复制标题
抽象和推理的游乐场
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
K. Morik
中科院分区：
文献类型：
--
作者：
Raphael Fischer;Matthias Jakobs;Sascha Mücke;K. Morik
当使用大型模型进行推理的研究成为人们关注的焦点时，一种使紧凑模型具有推理能力的符号方法也吸引了公众的注意。我们引入了Mini-ARC数据集，这是一个5 × 5的压缩版本，用于测量溯因推理能力。数据集很小，但很有创意，保持了原始数据集的难度，但提高了模型训练的可用性。沿着Mini-ARC 6，我们引入了O2 ARC界面，它包含了更丰富的功能，供人类7解决ARC任务。通过O2 ARC求解Mini-ARC，我们收集了8个人体轨迹，称为Mini-ARC轨迹
While research on reasoning using large models is in the spotlight, a symbolic 1 method of making a compact model capable of reasoning is also attracting public 2 attention. We introduce the Mini-ARC dataset, a 5x5 compact version of the 3 Abstraction and Reasoning Corpus (ARC) to measure the abductive reasoning 4 capability. The dataset is small but creative, which maintains the difficulty of the 5 original dataset but improves usability for model training. Along with Mini-ARC, 6 we introduce the O2ARC interface, which includes richer features for humans 7 to solve the ARC tasks. By solving Mini-ARC with O2ARC, we collect human 8 trajectories called Mini-ARC traces
DOI：
--
发表时间：
2021-06
期刊：
--
影响因子：
--
作者：
Lili Chen;Kevin Lu;A. Rajeswaran;Kimin Lee;Aditya Grover;M. Laskin;P. Abbeel;A. Srinivas;
通讯作者：
Lili Chen;Kevin Lu;A. Rajeswaran;Kimin Lee;Aditya Grover;M. Laskin;P. Abbeel;A. Srinivas;