We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more broadly applicable training objective for abductive reasoning, resulting in better interpretability and higher accuracy when solving Raven's progressive matrices (RPM). ARLC allows both programming domain knowledge and learning the rules underlying a data distribution. We evaluate ARLC on the I-RAVEN dataset, showcasing state-of-the-art accuracy across both in-distribution and out-of-distribution (unseen attribute-rule pairs) tests. ARLC surpasses neuro-symbolic and connectionist baselines, including large language models, despite having orders of magnitude fewer parameters. We show ARLC's robustness to post-programming training by incrementally learning from examples on top of programmed knowledge, which only improves its performance and does not result in catastrophic forgetting of the programmed solution. We validate ARLC's seamless transfer learning from a 2x2 RPM constellation to unseen constellations. Our code is available at https://github.com/IBM/abductive-rule-learner-with-context-awareness.

翻译：我们提出了具有上下文感知能力的溯因规则学习器（ARLC），这是一种基于Learn-VRF解决抽象推理任务的模型。ARLC采用了一种新颖且更广泛适用的溯因推理训练目标，在解决瑞文渐进矩阵（RPM）问题时实现了更好的可解释性和更高的准确率。ARLC既支持编程领域知识的融入，也能学习数据分布背后的规则。我们在I-RAVEN数据集上评估ARLC，展示了其在分布内测试和分布外（未见过的属性-规则组合）测试中均达到最先进的准确率。尽管参数量级显著减少，ARLC仍超越了神经符号系统和连接主义基线模型（包括大语言模型）。通过演示在编程知识基础上进行增量学习的能力，我们验证了ARLC对编程后训练的鲁棒性——这种学习方式仅提升其性能而不会导致编程解决方案的灾难性遗忘。我们证实了ARLC能够从2x2 RPM构型无缝迁移学习到未见过的构型。代码已开源：https://github.com/IBM/abductive-rule-learner-with-context-awareness。