# Contrastive Chain-of-Thought Prompting

arXiv: https://arxiv.org/abs/2311.09277 · HTML: https://mlsanity.com/paper/2311.09277/

## Key facts

- Cited by 52 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 5 of its 26 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## 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, 5 of 5)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [It Takes Two to Tango: Combining Visual and Textual Information for Detecting Duplicate Video-Based Bug Reports](https://mlsanity.com/paper/2101.09194/) (2021)

## Built on by (most cited first, 30 of 52)

- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Efficient Large Language Models: A Survey](https://mlsanity.com/paper/2312.03863/) (2023)
- [Recursive Introspection: Teaching Language Model Agents How to Self-Improve](https://mlsanity.com/paper/2407.18219/) (2024)
- [Are DeepSeek R1 And Other Reasoning Models More Faithful?](https://mlsanity.com/paper/2501.08156/) (2025)
- [Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning](https://mlsanity.com/paper/2403.02333/) (2024)
- [A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks](https://mlsanity.com/paper/2407.12994/) (2024)
- [In-Context Principle Learning from Mistakes](https://mlsanity.com/paper/2402.05403/) (2024)
- [A Theoretical Understanding of Self-Correction through In-context Alignment](https://mlsanity.com/paper/2405.18634/) (2024)
- [Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?](https://mlsanity.com/paper/2410.23856/) (2024)
- [From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium](https://mlsanity.com/paper/2506.08292/) (2025)
- [Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch](https://mlsanity.com/paper/2410.18693/) (2024)
- [Activation Steering for Chain-of-Thought Compression](https://mlsanity.com/paper/2507.04742/) (2025)
- [Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation](https://mlsanity.com/paper/2402.14874/) (2024)
- [Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns](https://mlsanity.com/paper/2404.14812/) (2024)
- [Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning](https://mlsanity.com/paper/2402.18344/) (2024)
- [Large Language Models are Contrastive Reasoners](https://mlsanity.com/paper/2403.08211/) (2024)
- [Rethinking Chain-of-Thought from the Perspective of Self-Training](https://mlsanity.com/paper/2412.10827/) (2024)
- [Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations](https://mlsanity.com/paper/2504.05294/) (2025)
- [Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience](https://mlsanity.com/paper/2506.00842/) (2025)
- [Baichuan Alignment Technical Report](https://mlsanity.com/paper/2410.14940/) (2024)
- [Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation](https://mlsanity.com/paper/2412.03944/) (2024)
- [Computational Argumentation-based Chatbots: a Survey](https://mlsanity.com/paper/2401.03454/) (2024)
- [ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning](https://mlsanity.com/paper/2505.19080/) (2025)
- ["Let's Argue Both Sides": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities](https://mlsanity.com/paper/2410.12997/) (2024)
- [Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning](https://mlsanity.com/paper/2510.20098/) (2025)
- [Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning](https://mlsanity.com/paper/2607.01511/) (2026)
- [Can formal argumentative reasoning enhance LLMs performances?](https://mlsanity.com/paper/2405.13036/) (2024)
- [RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance](https://mlsanity.com/paper/2412.09614/) (2024)
- [Improving RAG for Personalization with Author Features and Contrastive Examples](https://mlsanity.com/paper/2504.08745/) (2025)

## Abstract (arXiv)

Despite the success of chain of thought in enhancing language model reasoning, the underlying process remains less well understood. Although logically sound reasoning appears inherently crucial for chain of thought, prior studies surprisingly reveal minimal impact when using invalid demonstrations instead. Furthermore, the conventional chain of thought does not inform language models on what mistakes to avoid, which potentially leads to more errors. Hence, inspired by how humans can learn from both positive and negative examples, we propose contrastive chain of thought to enhance language model reasoning. Compared to the conventional chain of thought, our approach provides both valid and invalid reasoning demonstrations, to guide the model to reason step-by-step while reducing reasoning mistakes. To improve generalization, we introduce an automatic method to construct contrastive demonstrations. Our experiments on reasoning benchmarks demonstrate that contrastive chain of thought can serve as a general enhancement of chain-of-thought prompting.