paper-with-me

Papers

GPT Can Solve Mathematical Problems Without a Calculator

2023-09-06 · Zhen Yang, Ming Ding, Qingsong Lv, Zhihuan Jiang, Zehai He, Yuyi Guo, Jinfeng Bai, Jie Tang

Previous studies have typically assumed that large language models are unable to accurately perform arithmetic operations, particularly multiplication of >8 digits, and operations involving decimals and fractions, without the use of calculator tools. This paper aims to challenge this misconception. With sufficient training data, a 2 billion-parameter language model can accurately perform multi-digit arithmetic operations with almost 100% accuracy without data leakage, significantly surpassing GPT-4 (whose multi-digit multiplication accuracy is only 4.3%). We also demonstrate that our MathGLM, fine-tuned from GLM-10B on a dataset with additional multi-step arithmetic operations and math problems described in text, achieves similar performance to GPT-4 on a 5,000-samples Chinese math problem test set. Our code and data are public at https://github.com/THUDM/MathGLM.

📄 PDF Abstract BibTeX arXiv:2309.03241

Code (1)

thudm/mathglm 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingMath

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Image-to-image Neural Network for Addition and Subtraction of a Pair of Not Very Large Numbers

2020-03-14 · Vladimir Ivashkin

Looking back at the history of calculators, one can see that they become less functional and more computationally expensive over time. A modern calculator runs on a personal computer and is drawn at 60 fps only to help u…

Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models

2024-04-22 · Vishruth Veerendranath, Vishwa Shah, Kshitish Ghate

Quantitative and numerical comprehension in language is an important task in many fields like education and finance, but still remains a challenging task for language models. While tool and calculator usage has shown to …

DecoderMathematical Reasoning

IGC: Integrating a Gated Calculator into an LLM to Solve Arithmetic Tasks Reliably and Efficiently

2025-01-01 · Florian Dietz, Dietrich Klakow

Solving arithmetic tasks is a simple and fundamental skill, yet modern Large Language Models (LLMs) have great difficulty with them. We introduce the Integrated Gated Calculator (IGC), a module that enables LLMs to perfo…

GPU

Towards a Deterministic Math Solver for Clinical Language Models

2026-09-09 · Felipe Ocampo Osorio, Sebastián Andrés Cajas Ordoñez, Maximin Lange, Rafi Al Attrach 외 hf

Large language models are unreliable at arithmetic, which is a problem for clinical calculators where a single numerical error changes the recommendation. The standard response is to hardcode each calculator as a validat…

The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models

2026-05-11 · Cedric Flamant, Udaya Ghai, Kanna Shimizu arxiv

Existing multi-model and tool-augmented systems communicate by generating text, serializing every exchange through the output vocabulary. Can two pretrained language models instead coordinate through a continuous, concur…

Mathematical Reasoning