# Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs

arXiv: https://arxiv.org/abs/2509.10377 · HTML: https://mlsanity.com/paper/2509.10377/

## Key facts

- Cited by 25 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 28 of its 41 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Git Re-Basin: Merging Models modulo Permutation Symmetries](https://mlsanity.com/paper/2209.04836/) (2022)
- [On the Representation Collapse of Sparse Mixture of Experts](https://mlsanity.com/paper/2204.09179/) (2022)
- [Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy](https://mlsanity.com/paper/2310.01334/) (2023)
- [Task-Specific Expert Pruning for Sparse Mixture-of-Experts](https://mlsanity.com/paper/2206.00277/) (2022)
- [MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router](https://mlsanity.com/paper/2410.12013/) (2024)
- [Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering](https://mlsanity.com/paper/2409.16167/) (2024)
- [MoE-I2: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition](https://mlsanity.com/paper/2411.01016/) (2024)
- [Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs](https://mlsanity.com/paper/2407.00945/) (2024)
- [Mixture Compressor for Mixture-of-Experts LLMs Gains More](https://mlsanity.com/paper/2410.06270/) (2024)
- [Delta Decompression for MoE-based LLMs Compression](https://mlsanity.com/paper/2502.17298/) (2025)
- [SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models](https://mlsanity.com/paper/2410.14720/) (2024)
- [Reassessing Layer Pruning in LLMs: New Insights and Methods](https://mlsanity.com/paper/2411.15558/) (2024)
- [A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts](https://mlsanity.com/paper/2405.16646/) (2024)
- [From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches](https://mlsanity.com/paper/2503.08998/) (2025)
- [TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment](https://mlsanity.com/paper/2405.13911/) (2024)
- [Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning](https://mlsanity.com/paper/2412.00069/) (2024)
- [Enhancing Large Language Models through Structured Reasoning](https://mlsanity.com/paper/2506.20241/) (2025)

## Built on by (most cited first, 25 of 25)

- [Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL](https://mlsanity.com/paper/2602.13035/) (2026)
- [When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables](https://mlsanity.com/paper/2509.17680/) (2025)
- [EvoESAP: Non-Uniform Expert Pruning for Sparse MoE](https://mlsanity.com/paper/2603.06003/) (2026)
- [XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being](https://mlsanity.com/paper/2603.06583/) (2026)
- [Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search](https://mlsanity.com/paper/2601.03851/) (2026)
- [FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning](https://mlsanity.com/paper/2601.03938/) (2026)
- [FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models](https://mlsanity.com/paper/2604.02967/) (2026)
- [MoE Pathfinder: Trajectory-driven Expert Pruning](https://mlsanity.com/paper/2512.18425/) (2025)
- [How to Score Experts for One-Shot MoE Expert Pruning: A Unified Formulation and Selection Principle](https://mlsanity.com/paper/2606.15716/) (2026)
- [AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning](https://mlsanity.com/paper/2603.18492/) (2026)
- [Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression](https://mlsanity.com/paper/2603.02217/) (2026)
- [SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs](https://mlsanity.com/paper/2606.09886/) (2026)
- [Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning](https://mlsanity.com/paper/2511.07198/) (2025)
- [Frequency-Modulated Visual Restoration for Matryoshka Large Multimodal Models](https://mlsanity.com/paper/2603.11220/) (2026)
- [MoEITS: A Green AI approach for simplifying MoE-LLMs](https://mlsanity.com/paper/2604.10603/) (2026)
- [Eigenvectors of Experts are Training-free Non-collapsing Routers](https://mlsanity.com/paper/2605.30992/) (2026)
- [On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain](https://mlsanity.com/paper/2607.01444/) (2026)
- [Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment](https://mlsanity.com/paper/2511.08399/) (2025)
- [OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale](https://mlsanity.com/paper/2602.05711/) (2026)
- [Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning](https://mlsanity.com/paper/2604.15830/) (2026)
- [EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation](https://mlsanity.com/paper/2605.26785/) (2026)
- [Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models](https://mlsanity.com/paper/2605.28828/) (2026)
- [Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation](https://mlsanity.com/paper/2606.00232/) (2026)
- [VIA-SD: Verification via Intra-Model Routing for Speculative Decoding](https://mlsanity.com/paper/2606.12243/) (2026)
- [Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment](https://mlsanity.com/paper/2609.06076/) (2026)

## Abstract (arXiv)

Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert parameters, leading to high memory usage and challenges in deployment. Previous work has tried to reduce the overhead by pruning and merging experts, but primarily focused on expert-level operations, leaving neuron-level structure underexplored. We propose DERN (Dropping Experts, Recombining Neurons), a task-agnostic and retraining-free framework for expert pruning and reconstruction. We observe that experts are often misaligned and contain semantic conflicts at the neuron level, which poses challenges for direct merging. To solve this, DERN works in three steps: it first prunes redundant experts using router statistics; then it decomposes them into neuron-level expert segments, assigning each segment to its most compatible retained expert; and finally, it merges segments within each retained expert to build a compact representation. Experiments on Mixtral, Qwen, and DeepSeek SMoE models show that DERN improves performance by more than 5% on commonsense reasoning and MMLU benchmarks under 50% expert sparsity, without extra training. It also greatly reduces the number of experts and memory usage, making SMoE LLMs easier to deploy in practice.