用神经符号方法解决抽象推理难题，效率远超现有模型。
NSA: Neuro-symbolic ARC Challenge
- 结合Transformer与领域语言搜索，先生成候选方向再精准求解。
- 在ARC测试集上性能领先同类模型27%，训练集表现也优异。
- 适合对可解释性推理和少样本学习感兴趣的开发者与研究者。
抽象与推理语料库（ARC）评估了机器学习模型和组合搜索方法难以应对的通用推理能力。本文提出一种神经符号方法，利用Transformer生成候选解题路径，并结合领域特定语言进行组合搜索，大幅缩小搜索空间，使搜索在短时间内找到正确解。模型通过合成数据预训练，并在测试时生成特定任务的训练样本进行微调。实验表明，该方法在ARC测试集上相比现有最优模型提升27%，在训练集上表现同样出色。代码与数据集已公开于https://github.com/Batorskq/NSA。
原文摘要 · Abstract (English)
The Abstraction and Reasoning Corpus (ARC) evaluates general reasoning capabilities that are difficult for both machine learning models and combinatorial search methods. We propose a neuro-symbolic approach that combines a transformer for proposal generation with combinatorial search using a domain-specific language. The transformer narrows the search space by proposing promising search directions, which allows the combinatorial search to find the actual solution in short time. We pre-train the trainsformer with synthetically generated data. During test-time we generate additional task-specific training tasks and fine-tune our model. Our results surpass comparable state of the art on the ARC evaluation set by 27% and compare favourably on the ARC train set. We make our code and dataset publicly available at https://github.com/Batorskq/NSA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。