English
Related papers

Related papers: DynaMiCS: Fine-tuning LLMs with Performance Constr…

200 papers

Data mixing -- determining the ratios of data from different domains -- is a first-order concern for training language models (LMs). While existing mixing methods show promise, they fall short when applied during real-world LM development.…

Machine Learning · Computer Science 2026-02-13 Mayee F. Chen , Tyler Murray , David Heineman , Matt Jordan , Hannaneh Hajishirzi , Christopher Ré , Luca Soldaini , Kyle Lo

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…

Machine Learning · Computer Science 2026-04-17 Bingbing Wen , Sirajul Salekin , Feiyang Kang , Bill Howe , Lucy Lu Wang , Javier Movellan , Manjot Bilkhu

The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains. A common challenge when fine-tuning LLMs for domain-specific applications is the potential…

Computation and Language · Computer Science 2024-03-15 Jianwei Sun , Chaoyang Mei , Linlin Wei , Kaiyu Zheng , Na Liu , Ming Cui , Tianyi Li

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

Recent research has shown that large language models pretrained using unsupervised approaches can achieve significant performance improvement on many downstream tasks. Typically when adapting these language models to downstream tasks, like…

Computation and Language · Computer Science 2022-06-08 Xiaodi Sun , Sunny Rajagopalan , Priyanka Nigam , Weiyi Lu , Yi Xu , Belinda Zeng , Trishul Chilimbi

The data mixture used in the pre-training of a language model is a cornerstone of its final performance. However, a static mixing strategy is suboptimal, as the model's learning preferences for various data domains shift dynamically…

Machine Learning · Computer Science 2025-08-26 Yifan Wang , Binbin Liu , Fengze Liu , Yuanfan Guo , Jiyao Deng , Xuecheng Wu , Weidong Zhou , Xiaohuan Zhou , Taifeng Wang

Adapting large language models (LLMs) to low-resource languages (LRLs) is constrained by the scarcity of task data and computational resources. Although Proxy Tuning offers a logit-level strategy for introducing scaling effects, it often…

Computation and Language · Computer Science 2026-04-21 Chen Zhang , Jiuheng Lin , Zhiyuan Liao , Yansong Feng

Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy…

Machine Learning · Computer Science 2026-01-27 Jiapeng Wang , Changxin Tian , Kunlong Chen , Ziqi Liu , Jiaxin Mao , Wayne Xin Zhao , Zhiqiang Zhang , Jun Zhou

Language models (LMs) excel at tasks across diverse domains, yet require substantial computational resources during inference. Compression techniques such as pruning and quantization offer a practical path towards efficient LM deployment,…

Computation and Language · Computer Science 2026-02-26 Miles Williams , George Chrysostomou , Vitor Jeronymo , Nikolaos Aletras

Large language models (LLMs) are at the forefront of transforming numerous domains globally. However, their inclusivity and effectiveness remain limited for non-Latin scripts and low-resource languages. This paper tackles the imperative…

Computation and Language · Computer Science 2025-01-08 Somnath Kumar , Vaibhav Balloli , Mercy Ranjit , Kabir Ahuja , Tanuja Ganu , Sunayana Sitaram , Kalika Bali , Akshay Nambi

Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize…

Machine Learning · Computer Science 2026-01-16 Anvith Thudi , Evianne Rovers , Yangjun Ruan , Tristan Thrush , Chris J. Maddison

Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this.…

Computation and Language · Computer Science 2025-11-10 Yirong Zeng , Xiao Ding , Yuxian Wang , Weiwen Liu , Wu Ning , Yutai Hou , Xu Huang , Duyu Tang , Dandan Tu , Bing Qin , Ting Liu

The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks. However, this complexity also presents challenges, making LLMs…

Computation and Language · Computer Science 2023-10-24 Mingzhe Du , Anh Tuan Luu , Bin Ji , See-kiong Ng

Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of…

Computation and Language · Computer Science 2024-12-18 Jiawei Zheng , Hanghai Hong , Feiyan Liu , Xiaoli Wang , Jingsong Su , Yonggui Liang , Shikai Wu

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

Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of…

Computation and Language · Computer Science 2024-11-04 Yulong Wang , Chang Zuo , Yin Xuan , Hong Li , Ni Wei

Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degradation across…

Computation and Language · Computer Science 2025-05-28 Hexuan Deng , Wenxiang Jiao , Xuebo Liu , Jing Li , Min Zhang , Zhaopeng Tu

This research explores a hybrid approach to fine-tuning large language models (LLMs) by integrating real-world and synthetic data to boost model performance, particularly in generating accurate and contextually relevant responses. By…

Computation and Language · Computer Science 2024-10-15 Alexey Zhezherau , Alexei Yanockin

We propose a refined approach to efficiently fine-tune large language models (LLMs) on specific domains like the mathematical domain by employing a budgeted subset selection method. Our approach combines utility and diversity metrics to…

Machine Learning · Computer Science 2025-05-06 Madhav Kotecha , Vijendra Kumar Vaishya , Smita Gautam , Suraj Racha

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