Self-Consistency Improves Chain of Thought Reasoning in Language Models
This addresses the challenge of complex reasoning for AI applications, offering a significant but incremental improvement over existing chain-of-thought methods.
The paper tackles the problem of improving reasoning in language models by proposing self-consistency, a decoding strategy that samples multiple reasoning paths and selects the most consistent answer, resulting in performance boosts such as +17.9% on GSM8K and +11.0% on SVAMP.
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%).