PT-MoE combines low-rank prompt decomposition with routed expert prompts and reports gains over prompt tuning and LoRA across 17 QA and math datasets while using about 25% fewer parameters than LoRA.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
PT-MoE combines low-rank prompt decomposition with routed expert prompts and reports gains over prompt tuning and LoRA across 17 QA and math datasets while using about 25% fewer parameters than LoRA.