Contrastive Chain-of-Thought
Contrastive chain-of-thought adds both valid and deliberately invalid reasoning demonstrations to a prompt, so the model learns which mistakes to avoid as well as what correct reasoning looks like.
Description
The invalid demonstrations can be generated automatically by perturbing correct reasoning chains.
Sources
- Chia et al. (2023). Contrastive Chain-of-Thought Prompting.
Cite this entry
Protologue. (2026). Contrastive Chain-of-Thought. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0038). https://protologue.com/t/contrastive-chain-of-thought/
BibTeX
@misc{protologue_contrastive_chain_of_thought,
title = {Contrastive Chain-of-Thought},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0038},
url = {https://protologue.com/t/contrastive-chain-of-thought/}
}