# Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models

arXiv: https://arxiv.org/abs/2407.01906 · HTML: https://mlsanity.com/paper/2407.01906/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 37 of its 46 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 30 of 37)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [CLUE: A Chinese Language Understanding Evaluation Benchmark](https://mlsanity.com/paper/2004.05986/) (2020)
- [Hash Layers For Large Sparse Models](https://mlsanity.com/paper/2106.04426/) (2021)
- [Training Neural Networks with Fixed Sparse Masks](https://mlsanity.com/paper/2111.09839/) (2021)
- [Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning](https://mlsanity.com/paper/2109.05687/) (2021)
- [Composable Sparse Fine-Tuning for Cross-Lingual Transfer](https://mlsanity.com/paper/2110.07560/) (2021)
- [Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation](https://mlsanity.com/paper/2104.08771/) (2021)

## Built on by (most cited first, 21 of 21)

- [PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model](https://mlsanity.com/paper/2411.08212/) (2024)
- [AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections](https://mlsanity.com/paper/2505.12455/) (2025)
- [Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models](https://mlsanity.com/paper/2506.18945/) (2025)
- [When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2605.07260/) (2026)
- [Route Experts by Sequence, not by Token](https://mlsanity.com/paper/2511.06494/) (2025)
- [Continual Pre-training of MoEs: How robust is your router?](https://mlsanity.com/paper/2503.05029/) (2025)
- [DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models](https://mlsanity.com/paper/2601.04823/) (2026)
- [Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism](https://mlsanity.com/paper/2510.13170/) (2025)
- [Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation](https://mlsanity.com/paper/2604.03592/) (2026)
- [Modular Pretraining Enables Access Control](https://mlsanity.com/paper/2607.08077/) (2026)
- [LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing](https://mlsanity.com/paper/2603.12645/) (2026)
- [EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning](https://mlsanity.com/paper/2607.01789/) (2026)
- [Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices](https://mlsanity.com/paper/2508.19078/) (2025)
- [MoE-Sieve: Routing-Guided LoRA for Efficient MoE Fine-Tuning](https://mlsanity.com/paper/2603.24044/) (2026)
- [Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning](https://mlsanity.com/paper/2604.23036/) (2026)
- [ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts](https://mlsanity.com/paper/2606.01509/) (2026)
- [From Experts to Sub-experts: Fine-grained Parameter-Efficient Fine-Tuning for MoE LLMs](https://mlsanity.com/paper/2609.25655/) (2026)
- [Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning](https://mlsanity.com/paper/2604.06385/) (2026)
- [LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models](https://mlsanity.com/paper/2604.23809/) (2026)
- [RARE: Decoupling Representation Steering from Expert Routing in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2608.21236/) (2026)
- [MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference](https://mlsanity.com/paper/2609.34077/) (2026)

## Abstract (arXiv)

Parameter-efficient fine-tuning (PEFT) is crucial for customizing Large Language Models (LLMs) with constrained resources. Although there have been various PEFT methods for dense-architecture LLMs, PEFT for sparse-architecture LLMs is still underexplored. In this work, we study the PEFT method for LLMs with the Mixture-of-Experts (MoE) architecture and the contents of this work are mainly threefold: (1) We investigate the dispersion degree of the activated experts in customized tasks, and found that the routing distribution for a specific task tends to be highly concentrated, while the distribution of activated experts varies significantly across different tasks. (2) We propose Expert-Specialized Fine-Tuning, or ESFT, which tunes the experts most relevant to downstream tasks while freezing the other experts and modules; experimental results demonstrate that our method not only improves the tuning efficiency, but also matches or even surpasses the performance of full-parameter fine-tuning. (3) We further analyze the impact of the MoE architecture on expert-specialized fine-tuning. We find that MoE models with finer-grained experts are more advantageous in selecting the combination of experts that are most relevant to downstream tasks, thereby enhancing both the training efficiency and effectiveness. Our code is available at https://github.com/deepseek-ai/ESFT.