paper-with-me

홈 › Papers

Progressive Prompts: Continual Learning for Language Models

2023-01-29 · Anastasia Razdaibiedina, Yuning Mao, Rui Hou, Madian Khabsa, Mike Lewis, Amjad Almahairi

We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a large number of task-specific parameters. Progressive Prompts learns a new soft prompt for each task and sequentially concatenates it with the previously learned prompts, while keeping the base model frozen. Experiments on standard continual learning benchmarks show that our approach outperforms state-of-the-art methods, with an improvement >20% in average test accuracy over the previous best-preforming method on T5 model. We also explore a more challenging continual learning setup with longer sequences of tasks and show that Progressive Prompts significantly outperforms prior methods.

📄 PDF Abstract BibTeX arXiv:2301.12314

Code (2)

arazd/ProgressivePrompts 공식 구현 pytorch
arazd/residualprompts pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Attention 설명 없음
Test 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
Multi-Head Attention 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Learning Probabilistic Prompt for Continual Learning

2026-07-06 · Hyekang Park, Sanghoon Lee, Geon Lee, Jongyoun Noh 외 arxiv

Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint subset of classes, while preserving previously learned knowledge. Prompt-based continual learning methods propose to lea…

Continual Learning

POP: Prompt Of Prompts for Continual Learning

2023-06-14 · Zhiyuan Hu, Jiancheng Lyu, Dashan Gao, Nuno Vasconcelos

Continual learning (CL) has attracted increasing attention in the recent past. It aims to mimic the human ability to learn new concepts without catastrophic forgetting. While existing CL methods accomplish this to some e…

Continual LearningOpen-Ended Question Answering

LW2G: Learning Whether to Grow for Prompt-based Continual Learning

2024-09-27 · Qian Feng, Dawei Zhou, Hanbin Zhao, Chao Zhang 외

Continual Learning (CL) aims to learn in non-stationary scenarios, progressively acquiring and maintaining knowledge from sequential tasks. Recent Prompt-based Continual Learning (PCL) has achieved remarkable performance…

Continual LearningPrompt LearningRetrieval

Self-Boosting Large Language Models with Synthetic Preference Data

2024-10-09 · Qingxiu Dong, Li Dong, Xingxing Zhang, Zhifang Sui 외

Through alignment with human preferences, Large Language Models (LLMs) have advanced significantly in generating honest, harmless, and helpful responses. However, collecting high-quality preference data is a resource-int…

Instruction Following

PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning

2025-12-17 · Xiaodi Li, Dingcheng Li, Rujun Gao, Mahmoud Zamani 외 arxiv

Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired knowledge. A major obstacle in this setting is catastrophic …

Continual Learning