English
Related papers

Related papers: Unraveling LoRA Interference: Orthogonal Subspaces…

200 papers

Large language models (LLMs) suffer from catastrophic forgetting in sequential multi-task learning. Existing parameter regularization methods (e.g., O-LoRA, N-LoRA) mitigate interference via low-rank subspace orthogonality, but additive…

Computation and Language · Computer Science 2026-01-26 Kefan Cao , Shuaicheng Wu

Large Language Models (LLMs) have demonstrated impressive capabilities, but their high computational costs pose challenges for customization. Model merging offers a cost-effective alternative, yet existing methods suffer from interference…

Machine Learning · Computer Science 2025-02-19 Zhixiang Wang , Zhenyu Mao , Yixuan Qiao , Yunfang Wu , Biye Li

The scaling law of Large Language Models (LLMs) reveals a power-law relationship, showing diminishing return on performance as model scale increases. While training LLMs from scratch is resource-intensive, fine-tuning a pre-trained model…

Computation and Language · Computer Science 2025-05-22 Yiyun Zhou , Chang Yao , Jingyuan Chen

Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric misalignment between the merged encoder and static…

Machine Learning · Computer Science 2026-02-03 Fanshuang Kong , Richong Zhang , Zhijie Nie , Hang Zhou , Ziqiao Wang , Qiang Sun , Chunming Hu

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

Fine-tuning Large Language Models (LLMs) has become increasingly challenging due to their massive scale and associated computational costs. Parameter-Efficient Fine-Tuning (PEFT) methodologies have been proposed as computational…

Computation and Language · Computer Science 2025-05-22 Jialong Han , Si Zhang , Ke Zhang

Low-rank adaptations (LoRA) are widely used to fine-tune large models across various domains for specific downstream tasks. While task-specific LoRAs are often available, concerns about data privacy and intellectual property can restrict…

Machine Learning · Computer Science 2025-04-16 Hongxu Chen , Runshi Li , Bowei Zhu , Zhen Wang , Long Chen

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Machine Learning · Computer Science 2025-07-15 Seokmin Ko

Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment,…

Artificial Intelligence · Computer Science 2026-04-21 Anda Cao , Zhuo Gou , Yi Wang , Kaixuan Chen , Yu Wang , Can Wang , Mingli Song , Jie Song

Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Existing methods like data mixture strategies face limitations,…

Computation and Language · Computer Science 2026-02-03 Jinluan Yang , Dingnan Jin , Anke Tang , Li Shen , Didi Zhu , Zhengyu Chen , Ziyu Zhao , Daixin Wang , Qing Cui , Zhiqiang Zhang , Jun Zhou , Fei Wu , Kun Kuang

We propose Orthogonal Monte Carlo Dropout, a mechanism that enforces strict orthogonality when combining sparse semantic vectors without extra time complexity. Low-Rank Adaptation (LoRA), a popular fine-tuning method for large models,…

Machine Learning · Computer Science 2025-10-09 Andi Zhang , Xuan Ding , Haofan Wang , Steven McDonagh , Samuel Kaski

While post-training compression techniques effectively reduce the memory footprint, latency, and power consumption of Large Language Models (LLMs), they often result in noticeable accuracy degradation and remain limited by hardware and…

Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models (LLMs). However, achieving the right balance of data is crucial to prevent catastrophic forgetting and interference between tasks.…

Computation and Language · Computer Science 2024-03-07 Wenfeng Feng , Chuzhan Hao , Yuewei Zhang , Yu Han , Hao Wang

Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in diverse tasks across different domains, with an increasing focus on improving their zero-shot generalization capabilities for unseen multimodal tasks.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Ying Shen , Zhiyang Xu , Qifan Wang , Yu Cheng , Wenpeng Yin , Lifu Huang

Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA. Our findings suggest that the low-rank updating mechanism…

Computation and Language · Computer Science 2024-05-21 Ting Jiang , Shaohan Huang , Shengyue Luo , Zihan Zhang , Haizhen Huang , Furu Wei , Weiwei Deng , Feng Sun , Qi Zhang , Deqing Wang , Fuzhen Zhuang

Fine-tuning is a key approach for adapting language models to specific downstream tasks, but updating all model parameters becomes impractical as model sizes increase. Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank…

Computation and Language · Computer Science 2025-02-10 Jiayang Yu , Yihang Zhang , Bin Wang , Peiqin Lin , Yongkang Liu , Shi Feng

This study proposes a simple yet effective LoRA merge method to achieve LLM adaptation for low-resource language generation tasks. The LoRA merge technique, which integrates multiple LoRA modules trained on different tasks, has gained…

Computation and Language · Computer Science 2025-06-02 Ryota Miyano , Yuki Arase

Low-Rank Adaptation (LoRA) has emerged as a popular parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), yet it still incurs notable overhead and suffers from parameter interference in multi-task scenarios. We…

Machine Learning · Computer Science 2025-08-05 Juzheng Zhang , Jiacheng You , Ashwinee Panda , Tom Goldstein

Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. Despite extensive research, task interference remains a major…

Machine Learning · Computer Science 2026-02-25 Longhua Li , Lei Qi , Qi Tian , Xin Geng

Transformer-based large language models (LLMs) have achieved remarkable success across various tasks. Yet, fine-tuning such massive models in federated learning (FL) settings poses significant challenges due to resource constraints and…

Machine Learning · Computer Science 2026-03-25 Bumjun Kim , Wan Choi