CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning

2024/10/14 by Joshua Ong Jun Leang, Aryo Pradipta Gema, Leang, Joshua Ong Jun +3 · 7 citations
Computer Science · Mathematics · Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #Machine Learning (cs.LG) #Mathematics Education and Pedagogy #Mathematics Education and Teaching Techniques #Symbolic Computation (cs.SC)

paper · pdf · doi:10.48550/arxiv.2410.10336

openalex publication_date 2024/10/14 · openalex created_date 2024/10/20 · openalex updated_date 2026/07/28

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

Cited by

• Can Large Reasoning Models Improve Accuracy on Mathematical Tasks Using Flawed Thinking?
• DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
• One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning
• From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
• Systematic Optimization of Open Source Large Language Models for Mathematical Reasoning
• A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
• PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains

Related

• Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
• Faithful Chain-of-Thought Reasoning
• To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
• A Survey on Large Language Models for Mathematical Reasoning
• How Do Humans Write Code? Large Models Do It the Same Way Too