Iterative LLM refinement helps early in ideation and code, but in math only late under elaboration prompting; vague feedback tends to plateau or degrade quality.
Griffiths, Yuan Cao, and Karthik Narasimhan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting
Iterative LLM refinement helps early in ideation and code, but in math only late under elaboration prompting; vague feedback tends to plateau or degrade quality.