Logical Reasoning | Gabriele Sarti
Home
About me
Publications
Blog
Talks
Projects
Activities
CV
Communities
AI2S
AISIG
Logical Reasoning
DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
We propose DecoderLens, a method to interpret the iterative refinement of representations in encoder-decoder Transformer models.
Cite
×