SHIP jointly trains an encoder and decoder so a language model's soft-prompt parameters can be reconstructed from instructions and vice versa, improving instruction induction and inductive reasoning.
Bowman, and Omer Levy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Shuttle Between the Instructions and the Parameters of Large Language Models
SHIP jointly trains an encoder and decoder so a language model's soft-prompt parameters can be reconstructed from instructions and vice versa, improving instruction induction and inductive reasoning.