What Makes Math Word Problems Challenging for LLMs?
This work addresses the problem of improving LLM performance on math word problems for researchers and developers, but it is incremental as it focuses on analysis rather than new methods.
The paper investigates the linguistic and mathematical characteristics that make math word problems challenging for large language models, using feature-based classifiers to analyze and predict difficulty.
This paper investigates the question of what makes math word problems (MWPs) in English challenging for large language models (LLMs). We conduct an in-depth analysis of the key linguistic and mathematical characteristics of MWPs. In addition, we train feature-based classifiers to better understand the impact of each feature on the overall difficulty of MWPs for prominent LLMs and investigate whether this helps predict how well LLMs fare against specific categories of MWPs.