Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
In: Proceedings of the Genetic and Evolutionary Computation Conference
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Hop-based analysis of a real-world NP-hard problem reveals Leading Ones-like features, motivating the Leading Blocks Problem (LBP) that current genetic algorithms handle poorly.
citing papers explorer
-
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
-
The hop-like problem nature -- unveiling and modelling new features of real-world problems
Hop-based analysis of a real-world NP-hard problem reveals Leading Ones-like features, motivating the Leading Blocks Problem (LBP) that current genetic algorithms handle poorly.