A two-branch prompting method that exchanges answers between an original math question and a paraphrased version improves accuracy on several math benchmarks, but the gain is not separated from the extra compute or run-to-run variance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exchange of Perspective Prompting Enhances Reasoning in Large Language Models
A two-branch prompting method that exchanges answers between an original math question and a paraphrased version improves accuracy on several math benchmarks, but the gain is not separated from the extra compute or run-to-run variance.