English
Related papers

Related papers: GRAPE: Optimize Data Mixture for Group Robust Mult…

200 papers

Multimodal Large Language Model (MLLM) have demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve…

Computation and Language · Computer Science 2024-11-19 Wenke Huang , Jian Liang , Zekun Shi , Didi Zhu , Guancheng Wan , He Li , Bo Du , Dacheng Tao , Mang Ye

For green AI, it is crucial to measure and reduce the carbon footprint emitted during the training of large language models. In NLP, performing pre-training on Transformer models requires significant computational resources. This…

Computation and Language · Computer Science 2024-04-30 Sharayu Hiwarkhedkar , Saloni Mittal , Vidula Magdum , Omkar Dhekane , Raviraj Joshi , Geetanjali Kale , Arnav Ladkat

Selecting the best data mixture is critical for successful Supervised Fine-Tuning (SFT) of Multimodal Large Language Models. However, determining the optimal mixture weights across multiple domain-specific datasets remains a significant…

Machine Learning · Computer Science 2026-02-06 Davide Berasi , Matteo Farina , Massimiliano Mancini , Elisa Ricci

With the rapid development of natural language processing technology, large-scale language models (LLM) have achieved remarkable results in a variety of tasks. However, how to effectively train these huge models and improve their…

Artificial Intelligence · Computer Science 2024-12-09 Jiajing Chen , Bingying Liu , Xiaoxuan Liao , Jia Gao , Hongye Zheng , Yue Li

In the rapidly advancing arena of large language models (LLMs), a key challenge is to enhance their capabilities amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual…

Machine Learning · Computer Science 2024-03-04 Xuxi Chen , Zhendong Wang , Daouda Sow , Junjie Yang , Tianlong Chen , Yingbin Liang , Mingyuan Zhou , Zhangyang Wang

Continual pre-training on small-scale task-specific data is an effective method for improving large language models in new target fields, yet it risks catastrophic forgetting of their original capabilities. A common solution is to re-weight…

Machine Learning · Computer Science 2026-04-14 Kailai Yang , Xiao Liu , Lei Ji , Hao Li , Xiao Liang , Zhiwei Liu , Yeyun Gong , Peng Cheng , Mao Yang

Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Jianghui Wang , Yang Chen , Xingyu Xie , Cong Fang , Zhouchen Lin

The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These loops hinder efficient pipelining and scheduling of the…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-12-30 Nanda K. Unnikrishnan , Keshab K. Parhi

Prompt tuning has emerged as a lightweight strategy for adapting foundation models to downstream tasks, particularly for resource-constrained systems. As pre-trained prompts become valuable assets, combining multiple source prompts offers a…

Computation and Language · Computer Science 2025-10-16 Enming Zhang , Liwen Cao , Yanru Wu , Zijie Zhao , Yang Li

The analysis of software requirement specifications (SRS) using Natural Language Processing (NLP) methods has been an important study area in the software engineering field in recent years. Especially thanks to the advances brought by deep…

Software Engineering · Computer Science 2023-01-03 Savas Yildirim , Mucahit Cevik , Devang Parikh , Ayse Basar

Large Language Models (LLMs), being generic task solvers, are versatile. However, despite the vast amount of data they are trained on, there are speculations about their adaptation capabilities to a new domain. Additionally, the simple…

Computation and Language · Computer Science 2025-09-03 Anum Afzal , Mehul Kumawat , Florian Matthes

Data augmentation is an essential technique in natural language processing (NLP) for enriching training datasets by generating diverse samples. This process is crucial for improving the robustness and generalization capabilities of NLP…

Computation and Language · Computer Science 2025-10-16 Zaitian Wang , Jinghan Zhang , Xinhao Zhang , Kunpeng Liu , Pengfei Wang , Yuanchun Zhou

While domain adaptation methods address data shifts, most assume target populations align with at least one source population, neglecting mixtures that combine sources influenced by factors like demographics. Additional challenges in…

Methodology · Statistics 2025-05-02 Keyao Zhan , Xin Xiong , Zijian Guo , Tianxi Cai , Molei Liu

Multi-domain fine-tuning of large language models requires improving performance on target domains while preserving performance on constrained domains, such as general knowledge, instruction following, or safety evaluations. Existing data…

Machine Learning · Computer Science 2026-05-12 Eleonora Gualdoni , Sonia Laguna , Louis Bethune , Joao Monteiro , Pierre Ablin , Marco Cuturi

Large Language Models (LLMs) have shown remarkable capabilities across various natural language processing tasks but often struggle to excel uniformly in diverse or complex domains. We propose a novel ensemble method - Diverse Fingerprint…

Machine Learning · Computer Science 2025-02-10 Seffi Cohen , Niv Goldshlager , Nurit Cohen-Inger , Bracha Shapira , Lior Rokach

Multilingual models are parameter-efficient and especially effective in improving low-resource languages by leveraging crosslingual transfer. Despite recent advance in massive multilingual translation with ever-growing model and data, how…

Computation and Language · Computer Science 2021-12-01 Xian Li , Hongyu Gong

Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data inputs, especially for MLLMs that have been fine-tuned for…

Computation and Language · Computer Science 2025-07-02 Yang Dai , Jianxiang An , Tianwei Lin , Hongyang He , Hongzhe Huang , Wenqiao Zhang , Zheqi Lv , Siliang Tang , Yueting Zhuang

Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and require retraining when new data is introduced. To this end, we…

Machine Learning · Computer Science 2025-06-02 Wanyun Xie , Francesco Tonin , Volkan Cevher

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Computation and Language · Computer Science 2025-10-21 Mingye Zhu , Yi Liu , Zheren Fu , Yongdong Zhang , Zhendong Mao

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…