Learning to Reason With Relational Abstractions
This work addresses the challenge of enhancing multi-step reasoning in language models, which is incremental but offers specific gains for mathematical problem-solving.
The paper tackles the problem of improving systematic reasoning in language models for mathematical tasks by introducing relational abstractions to structure solution sequences, resulting in significantly higher accuracy compared to previous methods.
Large language models have recently shown promising progress in mathematical reasoning when fine-tuned with human-generated sequences walking through a sequence of solution steps. However, the solution sequences are not formally structured and the resulting model-generated sequences may not reflect the kind of systematic reasoning we might expect an expert human to produce. In this paper, we study how to build stronger reasoning capability in language models using the idea of relational abstractions. We introduce new types of sequences that more explicitly provide an abstract characterization of the transitions through intermediate solution steps to the goal state. We find that models that are supplied with such sequences as prompts can solve tasks with a significantly higher accuracy, and models that are trained to produce such sequences solve problems better than those that are trained with previously used human-generated sequences and other baselines. Our work thus takes several steps toward elucidating and improving how language models perform on tasks requiring multi-step mathematical reasoning.