English
Related papers

Related papers: MergeMix: Optimizing Mid-Training Data Mixtures vi…

200 papers

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

Computation and Language · Computer Science 2024-10-15 Aakanksha , Arash Ahmadian , Seraphina Goldfarb-Tarrant , Beyza Ermis , Marzieh Fadaee , Sara Hooker

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…

Machine Learning · Computer Science 2026-05-14 Paul Jeha , Anastasiia Sedova , Louis Béthune , Skyler Seto , Jes Frellsen , Pierre Ablin , Natalie Schluter

Large Language Models improve with increasing amounts of high-quality training data. However, leveraging larger datasets requires balancing quality, quantity, and diversity across sources. After evaluating nine baseline methods under both…

Computation and Language · Computer Science 2025-01-27 William Held , Bhargavi Paranjape , Punit Singh Koura , Mike Lewis , Frank Zhang , Todor Mihaylov

Training data compositions for Large Language Models (LLMs) can significantly affect their downstream performance. However, a thorough data ablation study exploring large sets of candidate data mixtures is typically prohibitively expensive…

Computation and Language · Computer Science 2024-12-10 Clara Na , Ian Magnusson , Ananya Harsh Jha , Tom Sherborne , Emma Strubell , Jesse Dodge , Pradeep Dasigi

Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…

Machine Learning · Computer Science 2025-10-21 Yifei He , Siqi Zeng , Yuzheng Hu , Rui Yang , Tong Zhang , Han Zhao

Model merging combines multiple models into a single model with aggregated capabilities, making it a powerful tool for large language model (LLM) development. However, scaling model merging is challenging: performance depends on the choice…

Machine Learning · Computer Science 2026-02-03 Oliver Bolton , Aakanksha , Arash Ahmadian , Sara Hooker , Marzieh Fadaee , Beyza Ermis

Optimizing data mixtures for supervised fine-tuning (SFT) of large language models (LLMs) is critical for developing general-purpose models, yet this area remains underexplored. In this paper, we frame data mixing as an optimization problem…

Artificial Intelligence · Computer Science 2025-08-19 Yuan Li , Zhengzhong Liu , Eric Xing

Large language models (LLMs) are now available from cloud API providers in various sizes and configurations. While this diversity offers a broad spectrum of choices, effectively leveraging the options to optimize computational cost and…

Large Language Models (LLMs) require instruction fine-tuning to perform different downstream tasks. However, the instruction fine-tuning phase still demands significant computational resources and labeled data, lacking a paradigm that can…

Computation and Language · Computer Science 2025-03-10 Yiguan Lin , Bin Xu , Yinghao Li , Yang Gao

Quality and diversity are two critical metrics for the training data of large language models (LLMs), positively impacting performance. Existing studies often optimize these metrics separately, typically by first applying quality filtering…

Computation and Language · Computer Science 2025-04-29 Fengze Liu , Weidong Zhou , Binbin Liu , Zhimiao Yu , Yifan Zhang , Haobin Lin , Yifeng Yu , Bingni Zhang , Xiaohuan Zhou , Taifeng Wang , Yong Cao

Fine-tuning a task-specific multilingual large language model (LLM) involves training the model on a multilingual dataset with examples in all the required languages. Updating one or more supported languages with additional data or adding…

Computation and Language · Computer Science 2026-01-26 Alphaeus Dmonte , Vidhi Gupta , Daniel J Perry , Mark Arehart

Large Language Models (LLMs) remain heavily centered on English, with limited performance in low-resource languages. Existing adaptation approaches, such as continual pre-training, demand significant computational resources. In the case of…

Computation and Language · Computer Science 2026-03-31 Eneko Valero , Maria Ribalta i Albado , Oscar Sainz , Naiara Perez , German Rigau

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Artificial Intelligence · Computer Science 2025-03-28 Jiaqi Han , Jingwen Ye , Shunyu Liu , Haofei Zhang , Jie Song , Zunlei Feng , Mingli Song

The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise…

Computation and Language · Computer Science 2022-10-14 Dan Qiao , Chenchen Dai , Yuyang Ding , Juntao Li , Qiang Chen , Wenliang Chen , Min Zhang

Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. While promising, merging into a single model often suffers…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Akash Dhasade , Divyansh Jhunjhunwala , Milos Vujasinovic , Gauri Joshi , Anne-Marie Kermarrec

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Machine Learning · Computer Science 2025-02-12 Kunfeng Lai , Zhenheng Tang , Xinglin Pan , Peijie Dong , Xiang Liu , Haolan Chen , Li Shen , Bo Li , Xiaowen Chu

Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image…

Computer Vision and Pattern Recognition · Computer Science 2024-09-20 Huafeng Qin , Xin Jin , Hongyu Zhu , Hongchao Liao , Mounîm A. El-Yacoubi , Xinbo Gao

Reasoning capabilities represent a critical frontier for large language models (LLMs), but developing them requires extensive proprietary datasets and computational resources. One way to efficiently supplement capabilities with is by model…

Artificial Intelligence · Computer Science 2025-06-26 Guinan Su , Jonas Geiping

The data used to pretrain large language models has a decisive impact on a model's downstream performance, which has led to a large body of work on data selection methods that aim to automatically determine the most suitable data to use for…

Computation and Language · Computer Science 2023-12-12 Alon Albalak , Liangming Pan , Colin Raffel , William Yang Wang

Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property…

Computation and Language · Computer Science 2025-05-23 Xisen Jin , Xiang Ren , Daniel Preotiuc-Pietro , Pengxiang Cheng