Prompting LLMs with distinct reasoning strategies and ensembling their outputs improves accuracy on logical deduction tasks, though not as consistently as the paper claims.
Hewett, Mojan Javaheripi, Piero Kauffmann, James R
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
-
Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize?
Prompting LLMs with distinct reasoning strategies and ensembling their outputs improves accuracy on logical deduction tasks, though not as consistently as the paper claims.