English
Related papers

Related papers: Merge to Mix: Mixing Datasets via Model Merging

200 papers

Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…

Computation and Language · Computer Science 2025-04-09 Jiho Gwak , Yuchul Jung

Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent works explore model merging to combine multiple task-specific models into a single multi-task model…

Computation and Language · Computer Science 2025-05-30 Haobo Zhang , Jiayu Zhou

Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large Language Models (LLMs). While previous model merging methods mainly focus on merging homogeneous models with…

Computation and Language · Computer Science 2026-04-23 Yiyang Du , Xiaochen Wang , Chi Chen , Jiabo Ye , Yiru Wang , Peng Li , Ming Yan , Ji Zhang , Fei Huang , Zhifang Sui , Maosong Sun , Yang Liu

Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. However, existing methods are brittle in practice and can…

Machine Learning · Computer Science 2025-04-08 Kevin Kuo , Amrith Setlur , Kartik Srinivas , Aditi Raghunathan , Virginia Smith

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

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach struggles with limited data in the context of low-resource…

Computation and Language · Computer Science 2025-02-10 Mingxu Tao , Chen Zhang , Quzhe Huang , Tianyao Ma , Songfang Huang , Dongyan Zhao , Yansong Feng

While LLMs excel at general tasks, they struggle in specialized domains like finance, requiring diverse skills in domain knowledge, mathematical reasoning, and multilingual processing. Merging domain-specific Continual Pre-training (CPT)…

Computation and Language · Computer Science 2025-11-05 Kentaro Ueda , François Portet , Hirohiko Suwa , Keiichi Yasumoto

Ensembling is a universally useful approach to boost the performance of machine learning models. However, individual models in an ensemble were traditionally trained independently in separate stages without information access about the…

Computer Vision and Pattern Recognition · Computer Science 2019-09-27 Hanhan Li , Joe Yue-Hei Ng , Paul Natsev

The performance of finetuned large language models (LLMs) hinges critically on the composition of the training mixture. However, selecting an optimal blend of task datasets remains a largely manual, heuristic driven process, with…

Retrieval-Augmented Generation (RAG) systems leverage Large Language Models (LLMs) to generate accurate and reliable responses that are grounded in retrieved context. However, LLMs often generate inconsistent outputs for semantically…

Computation and Language · Computer Science 2025-10-17 Xujun Peng , Anoop Kumar , Jingyu Wu , Parker Glenn , Daben Liu

Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstrated the effectiveness of combining parameters through…

Machine Learning · Computer Science 2025-12-02 Zhikang Chen , Sen Cui , Deheng Ye , Min Zhang , Gang Niu , Yu Zhang , Masashi Sugiyama , Tingting Zhu

Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream generalization under realistic compute and data budget…

Computation and Language · Computer Science 2026-04-21 Zhuo Chen , Yuxuan Miao , Supryadi , Deyi Xiong

Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a…

Machine Learning · Computer Science 2024-08-26 Nico Daheim , Thomas Möllenhoff , Edoardo Maria Ponti , Iryna Gurevych , Mohammad Emtiyaz Khan

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

The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So,…

Machine Learning · Computer Science 2021-12-16 Atindriyo Sanyal , Vikram Chatterji , Nidhi Vyas , Ben Epstein , Nikita Demir , Anthony Corletti

Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Shaoli Huang , Xinchao Wang , Dacheng Tao

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between…

Machine Learning · Computer Science 2025-10-28 Wenju Sun , Qingyong Li , Wen Wang , Yang Liu , Yangli-ao Geng , Boyang Li

We present a multiway fusion algorithm capable of directly processing uncertain pairwise affinities. In contrast to existing works that require initial pairwise associations, our MIXER algorithm improves accuracy by leveraging the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-04 Parker C. Lusk , Kaveh Fathian , Jonathan P. How

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Xiaoliang Liu , Furao Shen , Jian Zhao , Changhai Nie

Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task model, with strong performance across all tasks. When applied to all but the last layer of weights,…

Machine Learning · Computer Science 2024-10-17 Ekansh Sharma , Daniel M. Roy , Gintare Karolina Dziugaite