3 papers
cs.AI2023
Empirical Investigation of Neural Symbolic Reasoning Strategies
Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi +4
Neural reasoning accuracy improves when generating intermediate reasoning steps. However, the source of this improvement is yet unclear. Here, we investigate and factorize the bene…
cs.CL2023
Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?
Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi +4
Compositionality is a pivotal property of symbolic reasoning. However, how well recent neural models capture compositionality remains underexplored in the symbolic reasoning tasks.…
cs.LG2023
Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers
Yuta Matsumoto, Benjamin Heinzerling, Masashi Yoshikawa +1
How language models process complex input that requires multiple steps of inference is not well understood. Previous research has shown that information about intermediate values o…