PLPP regularizes learnable prompts with a top-k, mutual KL self-distillation loss computed through a no-training LM head, yielding small but consistent gains over PromptSRC.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models
PLPP regularizes learnable prompts with a top-k, mutual KL self-distillation loss computed through a no-training LM head, yielding small but consistent gains over PromptSRC.