# Recyclable Tuning for Continual Pre-training

arXiv: https://arxiv.org/abs/2305.08702 · HTML: https://mlsanity.com/paper/2305.08702/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 68 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [FNet: Mixing Tokens with Fourier Transforms](https://mlsanity.com/paper/2105.03824/) (2021)
- [Essentially No Barriers in Neural Network Energy Landscape](https://mlsanity.com/paper/1803.00885/) (2018)
- [Muppet: Massive Multi-task Representations with Pre-Finetuning](https://mlsanity.com/paper/2101.11038/) (2021)
- [Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models](https://mlsanity.com/paper/2203.06904/) (2022)

## Built on by (most cited first, 17 of 17)

- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [Continual Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2402.01364/) (2024)
- [Simple and Scalable Strategies to Continually Pre-train Large Language Models](https://mlsanity.com/paper/2403.08763/) (2024)
- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models](https://mlsanity.com/paper/2305.09955/) (2023)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [MUSCLE: A Model Update Strategy for Compatible LLM Evolution](https://mlsanity.com/paper/2407.09435/) (2024)
- [Efficient Model Development through Fine-tuning Transfer](https://mlsanity.com/paper/2503.20110/) (2025)
- [Is Extending Modality The Right Path Towards Omni-Modality?](https://mlsanity.com/paper/2506.01872/) (2025)
- [Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models](https://mlsanity.com/paper/2506.06844/) (2025)
- [LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades](https://mlsanity.com/paper/2505.13515/) (2025)
- [Policy Compatible Skill Incremental Learning via Lazy Learning Interface](https://mlsanity.com/paper/2509.20612/) (2025)
- [Towards Robust and Efficient Continual Language Learning](https://mlsanity.com/paper/2307.05741/) (2023)
- [Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining](https://mlsanity.com/paper/2510.22931/) (2025)
- [Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation](https://mlsanity.com/paper/2508.03571/) (2025)
- [BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs](https://mlsanity.com/paper/2602.17680/) (2026)
- [ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services](https://mlsanity.com/paper/2606.02606/) (2026)

## Abstract (arXiv)

Continual pre-training is the paradigm where pre-trained language models (PLMs) continually acquire fresh knowledge from growing data and gradually get upgraded. Before an upgraded PLM is released, we may have tuned the original PLM for various tasks and stored the adapted weights. However, when tuning the upgraded PLM, these outdated adapted weights will typically be ignored and discarded, causing a potential waste of resources. We bring this issue to the forefront and contend that proper algorithms for recycling outdated adapted weights should be developed. To this end, we formulate the task of recyclable tuning for continual pre-training. In pilot studies, we find that after continual pre-training, the upgraded PLM remains compatible with the outdated adapted weights to some extent. Motivated by this finding, we analyze the connection between continually pre-trained PLMs from two novel aspects, i.e., mode connectivity, and functional similarity. Based on the corresponding findings, we propose both an initialization-based method and a distillation-based method for our task. We demonstrate their feasibility in improving the convergence and performance for tuning the upgraded PLM. We also show that both methods can be combined to achieve better performance. The source codes are publicly available at https://github.com/thunlp/RecyclableTuning.