GRID combines output-space constrained decoding with gradient-guided prompt compression for task-agnostic, bounded-memory continual prompt tuning.
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when fine-tuned on pre-trained domains but also a non-decreasing performance on unseen ones. In this work, we first investigate such anytime fine-tuning effectiveness of existing continual pre-training approaches, concluding with unanimously decreased performance on unseen domains. To this end, we propose a prompt-guided continual pre-training method, where we train a hypernetwork to generate domain-specific prompts by both agreement and disagreement losses. The agreement loss maximally preserves the generalization of a pre-trained model to new domains, and the disagreement one guards the exclusiveness of the generated hidden states for each domain. Remarkably, prompts by the hypernetwork alleviate the domain identity when fine-tuning and promote knowledge transfer across domains. Our method achieved improvements of 3.57% and 3.4% on two real-world datasets (including domain shift and temporal shift), respectively, demonstrating its efficacy.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning
GRID combines output-space constrained decoding with gradient-guided prompt compression for task-agnostic, bounded-memory continual prompt tuning.