Arithmetic with Language Models: from Memorization to Computation

Abstract: A better understanding of the emergent computation and problem-solving capabilities of recent LLMs is of paramount importance to further improve them and broaden their applicability. This work investigates how a LLM, trained to predict the next token, can perform arithmetic computations generalizing beyond training data. Binary addition and multiplication constitute a good testbed for this purpose, since they require a very small vocabulary and exhibit relevant input/output discontinuities making smooth input interpolation ineffective for novel data. We successfully trained a light LLM to learn these tasks and ran a number of experiments to investigate the extrapolation capabilities and internal information processing. Our findings support the hypothesis that the LLM works as an Encoding-Regression-Decoding machine where the computation takes place in the value space once the input token representation is mapped to an appropriate internal representation.