2022

Limitations of Language Models in Arithmetic and Symbolic Induction

Qian, Jing, Wang, Hong, Li, Zekun et al.

Understand

Recent work has shown that large pretrained Language Models (LMs) can not only perform remarkably well on a range of Natural Language Processing (NLP) tasks but also start improving on reasoning tasks such as arithmetic induction, symbolic manipulation, and commonsense reasoning with increasing size of models.

  • However, it is still unclear what the underlying capabilities of these LMs are.
  • Surprisingly, we find that these models have limitations on certain basic symbolic manipulation tasks such as copy, reverse, and addition.
  • When the total number of symbols or repeating symbols increases, the model performance drops quickly.

Reading the bibliography…