Language Models Understand Numbers, at Least Partially

Anonymous

Abstract: Large language models (LLMs) have exhibited impressive competence in various tasks, but their opaque internal mechanisms hinder their use in mathematical problems.In this paper, we study a fundamental question: whether language models understand numbers, a basic element in math.Based on an assumption that LLMs should be capable of compressing numbers in their hidden states to solve mathematical problems, we construct a synthetic dataset comprising addition problems and utilize linear probes to read out input numbers from the hidden states.Experimental results support the existence of compressed numbers in LLMs.However, it is difficult to precisely reconstruct the original numbers, indicating that the compression process may not be lossless.Further experiments show that LLMs can utilize encoded numbers to perform arithmetic computations, and the computational ability scales up with the model size.Our preliminary research suggests that LLMs exhibit a partial understanding of numbers, offering insights for future investigations about the models' mathematical capability.

Paper Type: long

Research Area: Interpretability and Analysis of Models for NLP

Contribution Types: Model analysis & interpretability

Languages Studied: English