TextGrad is a powerful framework building automatic ``differentiation'' via text. TextGrad implements backpropagation through text feedback provided by LLMs, strongly building on the gradient metaphor

Activation patching studies the model's computation by altering its latent representations, the token embeddings in transformer-based language models, during the inference process

Patching

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

TextGrad

TextGrad: Automatic "Differentiation" via Text

The time-causal and time-recursive analogue of the Gabor transform provides a way to define a Gabor-like time-frequency analysis for real-time signals, for which the future cannot be accessed. This is achieved by choosing the temporal window function in a windowed Fourier transform as the time-causal limit kernel, which is a temporal kernel that is (i) time-causal, (ii) time-recursive and (iii) obeys temporal scale covariance.

Source	TextGrad: Automatic "Differentiation" via Text
Year
Data Source	Papers with Code archive (CC BY-SA)