A bottom-up, clustering-based taxonomy of LLM reasoning strategies enables predicting and steering model behavior, with training data format mattering more than domain.
Metacognitive capabilities of llms: An exploration in mathematical problem solving.Advances in Neural Information Processing Systems, 37:19783–19812, 2024
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
-
The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
A bottom-up, clustering-based taxonomy of LLM reasoning strategies enables predicting and steering model behavior, with training data format mattering more than domain.