Reasoning in Transformers - Mitigating Spurious Correlations and Reasoning Shortcuts

arXiv:2403.11314v1 Announce Type: new
Abstract: Transformer language models are neural networks used for a wide variety of tasks concerning natural language, including some that also require logical reasoning. However, a transformer model may easily learn spurious patterns in the data, short-circuiting actual reasoning. In this paper we investigate to what extent transformers can be trained to a) approximate reasoning in propositional logic while b) avoiding known reasoning shortcuts via spurious correlations in the training data. To do so, we use …

abstract arxiv correlations cs.cl cs.lg data however language language models learn natural natural language networks neural networks paper patterns reasoning tasks transformer transformer language models transformer model transformers type