AWhat changed
Sampled diverse reasoning paths and aggregated their answers to improve measured performance relative to greedy chain-of-thought decoding.
Scientific scope
Sampled diverse reasoning paths and aggregated their answers to improve measured performance relative to greedy chain-of-thought decoding. Year follows the 2022 preprint; ICLR publication was 2023. More sampled paths cost additional inference and consensus does not establish answer correctness.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Year follows the 2022 preprint; ICLR publication was 2023. More sampled paths cost additional inference and consensus does not establish answer correctness.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Google Research: self-consistency paper
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction