Empower Nested Boolean Logic via Self-Supervised Curriculum Learning
This addresses a core reasoning deficiency in language models, which is crucial for AI systems requiring robust logical inference, though it is incremental as it builds on existing training paradigms.
The paper tackled the problem that pre-trained language models perform poorly on multi-nested boolean logic, a fundamental reasoning task, and proposed a self-supervised curriculum learning method (CLR) that improved generalization to harder logic, showing it as a foundation for enhancing general logical tasks.
Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data. As opposed to constructing increasingly complex logic, this paper probes into the boolean logic, the root capability of a logical reasoner. We find that any pre-trained language models even including large language models only behave like a random selector in the face of multi-nested boolean logic, a task that humans can handle with ease. To empower language models with this fundamental capability, this paper proposes a new self-supervised learning method \textit{Curriculum Logical Reasoning} (\textsc{Clr}), where we augment the training data with nested boolean logic chain step-by-step, and program the training from simpler logical patterns gradually to harder ones. This new training paradigm allows language models to effectively generalize to much harder and longer-hop logic, which can hardly be learned through naive training. Furthermore, we show that boolean logic is a great foundation for improving the subsequent general logical tasks.