Plugin trains a small autoregressive model to multiply its softmax into a frozen LLM's softmax, adapting the output distribution to a target domain using only logits and limited data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Logits are All We Need to Adapt Closed Models
Plugin trains a small autoregressive model to multiply its softmax into a frozen LLM's softmax, adapting the output distribution to a target domain using only logits and limited data.