SLMs achieve only a 4.4% accuracy gain from self-generated hints on reasoning benchmarks, fail to semantically distinguish useful feedback, and perform worse with longer hints.
Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs
SLMs achieve only a 4.4% accuracy gain from self-generated hints on reasoning benchmarks, fail to semantically distinguish useful feedback, and perform worse with longer hints.