Task prompt vectors, formed by subtracting random initialization from tuned soft prompts, support low-resource initialization and arithmetic combination across tasks on 12 NLU datasets while remaining independent of initialization seed on two model architectures.
PPT : Pre-trained prompt tuning for few-shot learning
3 Pith papers cite this work, alongside 246 external citations. Polarity classification is still indexing.
3
Pith papers citing it
246
external citations · OpenAlex
fields
cs.CL 3verdicts
UNVERDICTED 3representative citing papers
RADS applies reinforcement learning to pick informative samples for transfer learning, improving performance over uncertainty and diversity sampling in low-resource imbalanced clinical settings.
LoRA-FA freezes LoRA's A matrix and trains only B with gradient corrections to approximate full fine-tuning gradients more closely.
citing papers explorer
-
Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
Task prompt vectors, formed by subtracting random initialization from tuned soft prompts, support low-resource initialization and arithmetic combination across tasks on 12 NLU datasets while remaining independent of initialization seed on two model architectures.
-
RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings
RADS applies reinforcement learning to pick informative samples for transfer learning, improving performance over uncertainty and diversity sampling in low-resource imbalanced clinical settings.
-
LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning
LoRA-FA freezes LoRA's A matrix and trains only B with gradient corrections to approximate full fine-tuning gradients more closely.