Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts (2025.acl-long)
Copied to clipboard
| Challenge: | Sparse Interpolated Mixture-of-Experts (SIMoE) instruction-tuning is an end-to-end algorithm designed to fine-tune a dense pre-trained Large Language Model (LLM) into a MoE-style model that possesses capabilities in multiple specialized domains. |
| Approach: | They propose an algorithm to fine-tune a dense pre-trained Large Language Model into a MoE-style model that possesses capabilities in multiple specialized domains. |
| Outcome: | The proposed algorithm achieves state-of-the-art on common instruction-tuning benchmarks while maintaining an optimal performance-compute trade-off compared to baselines. |
Similar Papers
Improved Sparse Upcycling for Instruction Tuning (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for sparse upcycling lead to performance degradation in instruction tuning scenarios. |
| Approach: | They propose a representation-based approach to convert dense language models into sparsely activated ones by initializing router weights from language models. |
| Outcome: | The proposed architecture improves model capabilities and routing consistency across multiple benchmarks. |
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated considerable proficiency in general natural language processing tasks. |
| Approach: | They propose a parameter-efficient sparsity crafting method which crafts dense models into sparse models using the mixture-of-experts architecture. |
| Outcome: | The proposed method significantly reduces computational costs and GPU memory requirements, while maintaining the quality of approximation in function space. |
Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on parameter-efficient fine-tuning (PEFT) for dense-architecture LLMs are lacking. |
| Approach: | They propose an expert-specialized fine-tuning method that tunes the experts most relevant to downstream tasks while freezing the other experts. |
| Outcome: | The proposed method matches or surpasses full-parameter fine-tuning. |
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for tuning large language models from dense to MoE face significant data requirements and require large-scale post-training. |
| Approach: | They propose an upcycling instruction tuning approach for tuning a dense pre-trained model into a MoE instruction model using genetic algorithm and parameter merging. |
| Outcome: | The proposed approach improves the performance of large language models with a small amount of seed data and improves their scaling. |
RECOST: External Knowledge Guided Data-efficient Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Considering the high computing power overhead, data-efficient instruction tuning is proposed to reduce the training data size. |
| Approach: | They propose a framework to improve instruction tuning by integrating external knowledge into a single pipeline. |
| Outcome: | The proposed method achieves better results with only 1% of the full dataset. |
MoExtend: Tuning New Experts for Modality and Task Extension (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing instruction tuning methods for large language models (LLMs) are costly and difficult to implement. |
| Approach: | They propose a framework to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. |
| Outcome: | The proposed framework enables rapid adaptation and extension to new modal data or tasks without tuning pretrained models. |
A Closer Look into Mixture-of-Experts in Large Language Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Mixture-of-experts (MoE) architectures are gaining increasing attention for their unique properties and remarkable performance. |
| Approach: | They propose a mixture-of-experts architecture that allows for model scaling without sacrificing computational efficiency. |
| Outcome: | The proposed model increases model size without sacrificing computational efficiency . the proposed model is modular and can be used by a broad spectrum of practitioners . |
MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs (2025.naacl-long)
Copied to clipboard
Yuhang Zhou, Giannis Karamanolakis, Victor Soto, Anna Rumshisky, Mayank Kulkarni, Furong Huang, Wei Ai, Jianhua Lu
| Challenge: | State-of-the-art methods for merging expert models with different architectures do not address parameter interference and require extensive fine-tuning to restore performance. |
| Approach: | They propose a method for merging experts with different architectures into a unified Mixture-of-Experts model with a goal of enhancing performance in each domain while retaining effectiveness on general tasks. |
| Outcome: | Experiments across multiple domains show that the proposed methods reduce fine-tuning costs and improve performance over state-of-the-art methods. |
HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)
Copied to clipboard
An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu
| Challenge: | Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization. |
| Approach: | They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts . |
| Outcome: | The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters. |
AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing MoE methods require a constant top-k routing for all tokens, which is restrictive because of the number of experts required for feature abstraction. |
| Approach: | They propose a token-adaptive routing method that allows different tokens to select a different number of experts. |
| Outcome: | a new method can reduce average expert load while achieving superior performance. |