TextGrad performs automatic differentiation for compound AI systems by backpropagating natural-language feedback from LLMs to optimize variables ranging from code to molecular structures.
We use these roles to let the user inject knowledge into the graph and guide the optimization behavior
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TextGrad: Automatic "Differentiation" via Text
TextGrad performs automatic differentiation for compound AI systems by backpropagating natural-language feedback from LLMs to optimize variables ranging from code to molecular structures.