Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Specifically,weperform soft theorem-proving by leveraging TLMs to generate natural language proofs. We test the generated proofs for logical consistency, along with the accuracy of the final inference.

Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from veryfewexamples,andcombining theserulestoformcompositional rule-based systems.

Decision trees are widely used in many settings where interpretable models are preferred orrequired.