ΑΙhub.org
 

Why ChatGPT struggles with math


by
07 November 2024



share this:

Have you ever tried to use an AI tool like ChatGPT to do some math and found it doesn’t always add up? It turns out there’s a reason for that.

As large language models (LLMs) like OpenAI’s ChatGPT become more ubiquitous, people increasingly rely on them for work and research assistance. Yuntian Deng, assistant professor at the David R. Cheriton School of Computer Science, discusses some of the challenges in LLMs’ reasoning capabilities, particularly in math, and explores the implications of using these models to aid problem-solving.

What flaw did you discover in ChatGPT’s ability to do math?

As I explained in a recent post on X, the latest reasoning variant of ChatGPT o1, struggles with large-digit multiplication, especially when multiplying numbers beyond nine digits. This is a notable improvement over the previous ChatGPT-4o model, which struggled even with four-digit multiplication, but it’s still a major flaw.

What implications does this have regarding the tool’s ability to reason?

Large-digit multiplication is a useful test of reasoning because it requires a model to apply principles learned during training to new test cases. Humans can do this naturally. For instance, if you teach a high school student how to multiply nine-digit numbers, they can easily extend that understanding to handle ten-digit multiplication, demonstrating a grasp of the underlying principles rather than mere memorization.

In contrast, LLMs often struggle to generalize beyond the data they have been trained on. For example, if an LLM is trained on data involving multiplication of up to nine-digit numbers, it typically cannot generalize to ten-digit multiplication.

As LLMs become more powerful, their impressive performance on challenging benchmarks can create the perception that they can “think” at advanced levels. It’s tempting to rely on them to solve novel problems or even make decisions. However, the fact that even o1 struggles with reliably solving large-digit multiplication problems indicates that LLMs still face challenges when asked to generalize to new tasks or unfamiliar domains.

Why is it important to study how these LLMs “think”?

Companies like OpenAI haven’t fully disclosed the details of how their models are trained or the data they use. Understanding how these AI models operate allows researchers to identify their strengths and limitations, which is essential for improving them. Moreover, knowing these limitations helps us understand which tasks are best suited for LLMs and where human expertise is still crucial.




University of Waterloo




            AIhub is supported by:


Related posts :



Introducing the NASA Onboard Artificial Intelligence Research (OnAIR) platform: an interview with Evana Gizzi

  03 Jul 2025
Find out about the OnAIR platform, some of the particular challenges of deploying AI-based solutions in space, and how the tool has been used so far.

An interview with Nicolai Ommer: the RoboCupSoccer Small Size League

  01 Jul 2025
We caught up with Nicolai to find out more about the Small Size League, how the auto referees work, and how teams use AI.

Forthcoming machine learning and AI seminars: July 2025 edition

  30 Jun 2025
A list of free-to-attend AI-related seminars that are scheduled to take place between 1 July and 31 August 2025.
monthly digest

AIhub monthly digest: June 2025 – gearing up for RoboCup 2025, privacy-preserving models, and mitigating biases in LLMs

  26 Jun 2025
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.

RoboCupRescue: an interview with Adam Jacoff

  25 Jun 2025
Find out what's new in the RoboCupRescue League this year.

Making optimal decisions without having all the cards in hand

Read about research which won an outstanding paper award at AAAI 2025.

Exploring counterfactuals in continuous-action reinforcement learning

  20 Jun 2025
Shuyang Dong writes about her work that will be presented at IJCAI 2025.

What is vibe coding? A computer scientist explains what it means to have AI write computer code − and what risks that can entail

  19 Jun 2025
Until recently, most computer code was written, at least originally, by human beings. But with the advent of GenAI, that has begun to change.



 

AIhub is supported by:






©2025.05 - Association for the Understanding of Artificial Intelligence


 












©2025.05 - Association for the Understanding of Artificial Intelligence