English
Related papers

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

200 papers

Pretrained Language Models (PLMs) have advanced Natural Language Processing (NLP) tasks significantly, but finetuning PLMs on low-resource datasets poses significant challenges such as instability and overfitting. Previous methods tackle…

Computation and Language · Computer Science 2024-03-20 Sai Ashish Somayajula , Youwei Liang , Abhishek Singh , Li Zhang , Pengtao Xie

Large Language Models (LLMs) have achieved impressive performance through Supervised Fine-tuning (SFT) on diverse instructional datasets. When training on multiple capabilities simultaneously, the mixture training dataset, governed by…

Artificial Intelligence · Computer Science 2025-05-20 Chenlin Ming , Chendi Qu , Mengzhang Cai , Qizhi Pei , Zhuoshi Pan , Yu Li , Xiaoming Duan , Lijun Wu , Conghui He

Despite the recent advancements of vision-language-action (VLA) models on a variety of robotics tasks, they suffer from critical issues such as poor generalizability to unseen tasks, due to their reliance on behavior cloning exclusively…

Robotics · Computer Science 2025-02-05 Zijian Zhang , Kaiyuan Zheng , Zhaorun Chen , Joel Jang , Yi Li , Siwei Han , Chaoqi Wang , Mingyu Ding , Dieter Fox , Huaxiu Yao

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

Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language…

Robotics · Computer Science 2025-02-24 Joey Hejna , Chethan Bhateja , Yichen Jiang , Karl Pertsch , Dorsa Sadigh

Training large language models with data collected from various domains can improve their performance on downstream tasks. However, given a fixed training budget, the sampling proportions of these different domains significantly impact the…

Computation and Language · Computer Science 2025-05-29 Yajiao Liu , Congliang Chen , Junchi Yang , Ruoyu Sun

Large language models have demonstrated remarkable capabilities across various tasks, primarily attributed to the utilization of diversely sourced data. However, the impact of pretraining data composition on model performance remains poorly…

Machine Learning · Computer Science 2025-01-28 Ce Ge , Zhijian Ma , Daoyuan Chen , Yaliang Li , Bolin Ding

Training large language models (LLMs) efficiently while preserving model quality poses significant challenges, particularly with subbyte precision supported by state-of-the-art GPUs. Current mixed-precision training approaches either apply…

Machine Learning · Computer Science 2026-02-03 Yunjie Pan , Yongyi Yang , Hanmei Yang , Scott Mahlke

Large Language Model (LLM) based multi-agent systems have shown remarkable performance in various tasks, especially when enhanced through collaborative communication. However, current methods often rely on a fixed number of agents and…

Computation and Language · Computer Science 2025-07-24 Boyi Li , Zhonghan Zhao , Der-Horng Lee , Gaoang Wang

Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no…

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Computation and Language · Computer Science 2025-10-22 Rohit Patel

We propose a method to optimize language model pre-training data mixtures through efficient approximation of the cross-entropy loss corresponding to each candidate mixture via a Mixture of Data Experts (MDE). We use this approximation as a…

Machine Learning · Computer Science 2025-02-25 Lior Belenki , Alekh Agarwal , Tianze Shi , Kristina Toutanova

Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on automatic prompt…

Computation and Language · Computer Science 2024-02-06 Moxin Li , Wenjie Wang , Fuli Feng , Yixin Cao , Jizhi Zhang , Tat-Seng Chua

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their…

Computation and Language · Computer Science 2024-06-18 Tuc Nguyen , Thai Le

As language models scale, the amount of data they require grows -- yet many target data sources, such as low-resource languages or specialized domains, are inherently limited in size. A common strategy is to mix this scarce but valuable…

Machine Learning · Computer Science 2026-05-18 Anastasiia Sedova , Skyler Seto , Natalie Schluter , Pierre Ablin

Balancing multiple objectives is critical for user satisfaction in modern recommender and search systems, yet current Multi-Task Fusion (MTF) methods rely on static, manually-tuned weights that fail to capture individual user intent. While…

Machine Learning · Computer Science 2025-10-13 Tingfeng Hong , Pingye Ren , Xinlong Xiao , Chao Wang , Chenyi Lei , Wenwu Ou , Han Li

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

Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an adapter for each domain on the task of language modeling. This…

Computation and Language · Computer Science 2023-03-29 Alexandra Chronopoulou , Matthew E. Peters , Alexander Fraser , Jesse Dodge

Efficient finetuning of pretrained language transformers is becoming increasingly prevalent for solving natural language processing tasks. While effective, it can still require a large number of tunable parameters. This can be a drawback…

Computation and Language · Computer Science 2023-05-31 Umang Gupta , Aram Galstyan , Greg Ver Steeg

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

Computation and Language · Computer Science 2022-07-11 Zejiang Hou , Julian Salazar , George Polovets