Black-box prompt optimization yields small or negative gains on very large LLMs, and its benefit appears to shrink as model scale increases.
Advances in Neural Information Processing Systems , 33:1877–1901
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow
Black-box prompt optimization yields small or negative gains on very large LLMs, and its benefit appears to shrink as model scale increases.