GRID: Scalable Task-Agnostic Prompt-Based Continual Learning for Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915527039909888 |
|---|---|
| author | Tiwari, Anushka Pal, Sayantan Srihari, Rohini K. Ji, Kaiyi |
| author_facet | Tiwari, Anushka Pal, Sayantan Srihari, Rohini K. Ji, Kaiyi |
| contents | Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of task-specific prompts, which introduces two major challenges: (1) severe performance degradation on earlier tasks under task-agnostic inference, and (2) limited scalability due to prompt memory accumulation as task sequences grow. In this paper, we present GRID, a unified framework designed to address these challenges. GRID incorporates a decoding mechanism that enhances backward transfer by leveraging representative inputs, automatic task identification, and constrained decoding. Furthermore, it employs a gradient-guided prompt selection strategy to compress less informative prompts into a single aggregated representation, ensuring scalable and memory-efficient continual learning. Extensive experiments on long-sequence and negative transfer benchmarks show that GRID improves average accuracy and backward transfer, achieves competitive forward transfer, and substantially reduces prompt memory usage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14725 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GRID: Scalable Task-Agnostic Prompt-Based Continual Learning for Language Models Tiwari, Anushka Pal, Sayantan Srihari, Rohini K. Ji, Kaiyi Machine Learning Artificial Intelligence Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of task-specific prompts, which introduces two major challenges: (1) severe performance degradation on earlier tasks under task-agnostic inference, and (2) limited scalability due to prompt memory accumulation as task sequences grow. In this paper, we present GRID, a unified framework designed to address these challenges. GRID incorporates a decoding mechanism that enhances backward transfer by leveraging representative inputs, automatic task identification, and constrained decoding. Furthermore, it employs a gradient-guided prompt selection strategy to compress less informative prompts into a single aggregated representation, ensuring scalable and memory-efficient continual learning. Extensive experiments on long-sequence and negative transfer benchmarks show that GRID improves average accuracy and backward transfer, achieves competitive forward transfer, and substantially reduces prompt memory usage. |
| title | GRID: Scalable Task-Agnostic Prompt-Based Continual Learning for Language Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.14725 |