English
Related papers

Related papers: Replaying pre-training data improves fine-tuning

200 papers

In this paper we present an alternative strategy for fine-tuning the parameters of a network. We named the technique Gradual Tuning. Once trained on a first task, the network is fine-tuned on a second task by modifying a progressively…

Artificial Intelligence · Computer Science 2017-11-29 Guglielmo Montone , J. Kevin O'Regan , Alexander V. Terekhov

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Computation and Language · Computer Science 2023-10-24 Lingyu Gao , Debanjan Ghosh , Kevin Gimpel

Data mixing strategies have successfully reduced the costs involved in training language models. While promising, such methods suffer from two flaws. First, they rely on predetermined data domains (e.g., data sources, task types), which may…

In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption,…

Machine Learning · Computer Science 2020-01-24 Cheolhyoung Lee , Kyunghyun Cho , Wanmo Kang

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…

Computation and Language · Computer Science 2025-08-29 Hua Farn , Hsuan Su , Shachi H Kumar , Saurav Sahay , Shang-Tse Chen , Hung-yi Lee

Fine-tuning is a common practice in deep learning, achieving excellent generalization results on downstream tasks using relatively little training data. Although widely used in practice, it is lacking strong theoretical understanding. We…

Machine Learning · Computer Science 2021-11-09 Gal Shachaf , Alon Brutzkus , Amir Globerson

The creation of large-scale open domain reading comprehension data sets in recent years has enabled the development of end-to-end neural comprehension models with promising results. To use these models for domains with limited training…

Computation and Language · Computer Science 2020-11-23 Y. Xu , X. Zhong , A. J. J. Yepes , J. H. Lau

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1)…

We demonstrate that explicitly aligning the pretraining objectives to the finetuning objectives in language model training significantly improves the finetuning task performance and reduces the minimum amount of finetuning examples…

Computation and Language · Computer Science 2020-02-07 Nuo Wang Pierse , Jingwen Lu

Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall…

Robotics · Computer Science 2026-03-03 Yajat Yadav , Zhiyuan Zhou , Andrew Wagenmaker , Karl Pertsch , Sergey Levine

This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel…

Computation and Language · Computer Science 2024-07-22 Michael Oliver , Guan Wang

Since compute grows much faster than web text available for language model pre-training, we ask how one should approach pre-training under fixed data and no compute constraints. We first show that existing data-constrained approaches of…

Machine Learning · Computer Science 2025-09-19 Konwoo Kim , Suhas Kotha , Percy Liang , Tatsunori Hashimoto

Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the…

Artificial Intelligence · Computer Science 2025-03-26 Ekin Akyürek , Mehul Damani , Adam Zweiger , Linlu Qiu , Han Guo , Jyothish Pari , Yoon Kim , Jacob Andreas

Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a significant performance drop on the original tasks. This paper…

Computation and Language · Computer Science 2024-02-20 Didi Zhu , Zhongyi Sun , Zexi Li , Tao Shen , Ke Yan , Shouhong Ding , Kun Kuang , Chao Wu

A recent family of techniques, dubbed lightweight fine-tuning methods, facilitates parameter-efficient transfer learning by updating only a small set of additional parameters while keeping the parameters of the pretrained language model…

Computation and Language · Computer Science 2022-12-09 Mozhdeh Gheini , Xuezhe Ma , Jonathan May

Foundation models for tabular data, like TabPFN, achieve strong performance on small datasets when pre-trained solely on synthetic data. We show that this performance can be significantly boosted by a targeted continued pre-training phase.…

Machine Learning · Computer Science 2025-07-08 Anurag Garg , Muhammad Ali , Noah Hollmann , Lennart Purucker , Samuel Müller , Frank Hutter

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., the language model pre-trained on static data from past years performs worse over time on emerging data. Existing…

Computation and Language · Computer Science 2022-11-01 Zhaochen Su , Zecheng Tang , Xinyan Guan , Juntao Li , Lijun Wu , Min Zhang

Despite their success in many natural language tasks, solving math problems remains a significant challenge for large language models (LLMs). A large gap exists between LLMs' pass-at-one and pass-at-N performance in solving math problems,…

Computation and Language · Computer Science 2023-10-17 Yixin Liu , Avi Singh , C. Daniel Freeman , John D. Co-Reyes , Peter J. Liu

There are growing interests in adapting large-scale language models using parameter-efficient fine-tuning methods. However, accelerating the model itself and achieving better inference efficiency through model compression has not been…

The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's…

Computation and Language · Computer Science 2023-03-28 Yunjie Ji , Yong Deng , Yan Gong , Yiping Peng , Qiang Niu , Lei Zhang , Baochang Ma , Xiangang Li