# Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns

arXiv: https://arxiv.org/abs/2404.14812 · HTML: https://mlsanity.com/paper/2404.14812/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 43 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 8 of 8)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [Progressive-Hint Prompting Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2304.09797/) (2023)
- [Rationale-Augmented Ensembles in Language Models](https://mlsanity.com/paper/2207.00747/) (2022)
- [Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models](https://mlsanity.com/paper/2302.00618/) (2023)
- [Contrastive Chain-of-Thought Prompting](https://mlsanity.com/paper/2311.09277/) (2023)
- [Using Captum to Explain Generative Language Models](https://mlsanity.com/paper/2312.05491/) (2023)

## Built on by (most cited first, 13 of 13)

- [AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation](https://mlsanity.com/paper/2509.25651/) (2025)
- [Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning](https://mlsanity.com/paper/2503.11655/) (2025)
- [ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning](https://mlsanity.com/paper/2512.00831/) (2025)
- [RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2505.13307/) (2025)
- [GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering](https://mlsanity.com/paper/2604.06794/) (2026)
- [Semi-structured LLM Reasoners Can Be Rigorously Audited](https://mlsanity.com/paper/2505.24217/) (2025)
- [PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning](https://mlsanity.com/paper/2508.09521/) (2025)
- [A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1](https://mlsanity.com/paper/2507.08621/) (2025)
- [Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy Evaluation](https://mlsanity.com/paper/2507.13238/) (2025)
- [Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping](https://mlsanity.com/paper/2603.06923/) (2026)
- [Don't Just Search, Understand: Semantic Path Planning Agent for Spherical Tensegrity Robots in Unknown Environments](https://mlsanity.com/paper/2511.01236/) (2025)
- [Dual-Process Scaffold Reasoning for Enhancing LLM Code Debugging](https://mlsanity.com/paper/2511.08052/) (2025)
- [DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extraction](https://mlsanity.com/paper/2608.22014/) (2026)

## Abstract (arXiv)

Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised CoT methods primarily select examples based on the semantics of the questions, which can introduce noise and lack interpretability. In this paper, we propose leveraging reasoning patterns to enhance CoT prompting effectiveness. Reasoning patterns represent the process by which language models arrive at their final results. By utilizing prior knowledge and prompt-based methods from large models, we first construct task-specific pattern sets. We then select diverse demonstrations based on different reasoning patterns. This approach not only mitigates the impact of noise but also provides explicit interpretability to help us understand the mechanisms of CoT. Extensive experiments demonstrate that our method is more robust and consistently leads to improvements across various reasoning tasks.