CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning

Joshua Ong Jun Leang, Aryo Pradipta Gema, Shay B. Cohen
10/14/2024
cs.AIcs.CLcs.LG

No official code found. Best implementation: joshuaongg21/CoMAT (10 stars, last commit 2024-12-09).

Abstract

Mathematical reasoning remains a significant challenge for large language models (LLMs), despite progress in prompting techniques such as Chain-of-Thought (CoT). We present **Chain of Mathematically Annotated Thought (CoMAT)**, which enhances reasoning through two stages: *Symbolic Conversion* (converting natural language queries into symbolic form) and *Reasoning Execution* (deriving answers from symbolic representations). CoMAT operates entirely with a single LLM and without external solvers. Across four LLMs, CoMAT outperforms traditional CoT on six out of seven benchmarks, achieving gains of 4.48% on MMLU-Redux (MATH) and 4.58% on GaoKao MCQ. In addition to improved performance, CoMAT ensures faithfulness and verifiability, offering a transparent reasoning process for complex mathematical tasks

View on arXivView PDF

Code Implementations(1)

joshuaongg21/CoMATCommunity100%
101Shell, PythonJun 20, 20241 years ago

Similar Papers

Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective

88% match2025

A Survey on Large Language Models for Mathematical Reasoning

86% match2025

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

86% match1 repo262024

KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?

86% match2025

Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning

85% match1 repo52023

How Do Humans Write Code? Large Models Do It the Same Way Too

85% match1 repo22024

Cite this paper

@article{leang2024comat,
  title  = {CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning},
  author = {Joshua Ong Jun Leang and Aryo Pradipta Gema and Shay B. Cohen},
  year   = {2024},
  eprint = {2410.10336},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.10336v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.10336.svg)](https://codeofpaper.com/paper/2410.10336)

Discussion