Self-Consistency Improves Chain of Thought Reasoning in Language Models

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought prompting. It first samples a diverse set of reasoning paths instead of only taking the greedy one, and then selects the most consistent answer by marginalizing out the sampled reasoning paths. Self-consistency leverages the intuition that a complex reasoning problem typically admits multiple different ways of thinking leading to its unique correct answer. Our extensive empirical evaluation shows that self-consistency boosts the performance of chain-of-thought prompting with a striking margin on a range of popular arithmetic and commonsense reasoning benchmarks, including GSM8K (+17.9%), SVAMP (+11.0%), AQuA (+12.2%), StrategyQA (+6.4%) and ARC-challenge (+3.9%).

PDF Abstract

Results from the Paper


Ranked #84 on Arithmetic Reasoning on GSM8K (using extra training data)

     Get a GitHub badge

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Uses Extra
Training Data
Source Paper Compare
Arithmetic Reasoning GSM8K PaLM 540B maj1@40 (8-shot) Accuracy 74.4 # 84
Parameters (Billion) 540 # 120

Methods


No methods listed for this paper. Add relevant methods here