Related papers: Linear Model Merging Unlocks Simple and Scalable M…

Model merging has emerged as an efficient strategy for constructing multitask models by integrating the strengths of multiple available expert models, thereby reducing the need to fine-tune a pre-trained model for all the tasks from…

Large language model (LLM) merging has become a key technique in modern LLM development pipelines, enabling the integration of multiple task- or domain-specific expert models without retraining. However, as the number of experts grows,…

Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Recent progress has shown that merging can be highly effective…

Mixture-of-Expert (MoE) based large language models (LLMs), such as the recent Mixtral and DeepSeek-MoE, have shown great promise in scaling model size without suffering from the quadratic growth of training cost of dense transformers. Like…

Federated learning (FL) is a collaborative machine learning approach that enables multiple clients to train models without sharing their private data. With the rise of deep learning, large-scale models have garnered significant attention…

Supervised fine-tuning (SFT) is widely used to align large language models (LLMs) with information extraction (IE) tasks, such as named entity recognition (NER). However, annotating such fine-grained labels and training domain-specific…

The Sparse Mixture of Experts (SMoE) has been widely employed to enhance the efficiency of training and inference for Transformer-based foundational models, yielding promising results.However, the performance of SMoE heavily depends on the…

The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention…

The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data…

Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant…

Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different domains and datasets. This paper examines the approach of…

Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism…

When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong…

In this study, we evaluate the effect of model merging in ad-hoc retrieval tasks. Model merging is a technique that combines the diverse characteristics of multiple models. We hypothesized that applying model merging to domain-specific…

While large-scale training data is fundamental for developing capable large language models (LLMs), strategically selecting high-quality data has emerged as a critical approach to enhance training efficiency and reduce computational costs.…

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a…

Direct Preference Optimization (DPO) has been widely adopted for large language model alignment due to its simple training procedure and lack of an explicit reward model. However, in iterative DPO, when the policy model from the previous…

Parameter-efficient fine-tuning techniques like Low-Rank Adaptation (LoRA) have revolutionized the adaptation of large language models (LLMs) to diverse tasks. Recent efforts have explored mixtures of LoRA modules for multi-task settings.…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Continual pre-training is widely used to adapt LLMs to target languages and domains, yet the mixture ratio of training data remains a sensitive hyperparameter that is expensive to tune: they must be fixed before training begins, and a…