mlsanityData to 14 Oct 2026

CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning

arXiv 2410.10336 ↗First posted 14 Oct 2024cs.AI cs.CL cs.LGcited by 16

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

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

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 47 of its 69 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

47 of 69 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models7 Oct
  2. 2024LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought9 May
  3. 2024Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems23 Apr
  4. 2024LeanReasoner: Boosting Complex Logical Reasoning with Lean20 Mar
  5. 2024Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models4 Mar
  6. 2024Large Language Models for Mathematical Reasoning: Progresses and Challenges31 Jan
  7. 2023Exploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoning21 Aug
  8. 2023A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers21 May
  9. 2023MathPrompter: Mathematical Reasoning using Large Language Models4 Mar
  10. 2022Language Models are Multilingual Chain-of-Thought Reasoners6 Oct

Other references · 37

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2024Qwen2 Technical Reportcited by 2,120
  7. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  8. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  9. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  10. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
  11. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  12. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
25 more
  1. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  2. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  3. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 441
  4. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  5. 2016Solving General Arithmetic Word Problemscited by 360
  6. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 291
  7. 2023Faithful Chain-of-Thought Reasoningcited by 288
  8. 2024Are We Done with MMLU?cited by 194
  9. 2023Evaluating the Performance of Large Language Models on GAOKAO Benchmarkcited by 186
  10. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  11. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 168
  12. 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Stepcited by 148
  13. 2022Holistic Evaluation of Language Modelscited by 131
  14. 2023Solving Math Word Problems by Combining Language Models With Symbolic Solverscited by 124
  15. 2024Faithful Logical Reasoning via Symbolic Chain-of-Thoughtcited by 100
  16. 2024Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Modelscited by 96
  17. 2024Changing Answer Order Can Decrease MMLU Accuracycited by 42
  18. 2024Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Provingcited by 35
  19. 2024Chain-of-Thought Unfaithfulness as Disguised Accuracycited by 28
  20. 2024Dissociation of Faithful and Unfaithful Reasoning in LLMscited by 23
  21. 2024Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulnesscited by 20
  22. 2022A Survey in Mathematical Language Processingcited by 9
  23. 2024Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Modelscited by 9
  24. 2024RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoningcited by 6
  25. 2024Fixing Function-Level Code Generation Errors for Foundation Large Language Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 5.

16 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scalingcited by 136
  3. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 25
  4. 2025Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractionscited by 17
  5. 2025Theorem Prover as a Judge for Synthetic Data Generationcited by 14
  6. 2025From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoningcited by 12
  7. 2025PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chainscited by 10
  8. 2025DTS: Enhancing Large Reasoning Models via Decoding Tree Sketchingcited by 6
  9. 2026Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisationcited by 4
  10. 2025Can Large Reasoning Models Improve Accuracy on Mathematical Tasks Using Flawed Thinking?cited by 2
  11. 2025One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoningcited by 1
  12. 2026Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Modelscited by 1
4 more
  1. 2025Systematic Optimization of Open Source Large Language Models for Mathematical Reasoningcited by 0
  2. 2026Value-Aware Numerical Representations for Transformer Language Modelscited by 0
  3. 2026Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Modelscited by 0
  4. 2026When Tokenization is Secretly Output Supervisioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  3. 2025Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
  4. 2025Thinking Machines: Mathematical Reasoning in the Age of LLMs
  5. 2025A Survey on Large Language Models for Mathematical Reasoning
  6. 2023Learning Multi-Step Reasoning by Solving Arithmetic Tasks
  7. 2025Analyzing the Power of Chain of Thought through Memorization Capabilities
  8. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective