Skip to content
AImpact
IT EN
High Foundation Models · 1 min read

Self-Consistency: sample multiple reasoning paths for better answers

In one sentence Wang et al. (Google Brain) show that sampling N diverse reasoning paths and taking the most frequent answer beats greedy decoding on all reasoning benchmarks.

Verified Official source
ShareLinkedInX
Reading level

When you ask a model to solve a problem, it usually takes the "most likely" path to the answer. Self-Consistency does something different: it asks the model to solve the same problem many times in different ways, then picks the answer that shows up most often.

It's like asking ten people to solve a math problem independently and then voting on the result: even if someone makes a mistake, the majority gets it right.

The outcome is surprising: without changing anything in the model, just by sampling multiple times, you get large improvements on arithmetic and logical reasoning.

Companies

Google

Tools

PaLM, GPT-3

Tags

Chain of ThoughtSelf-ConsistencyReasoningGoogle BrainPrompting

Sources