# Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis

arXiv: https://arxiv.org/abs/2505.24593 · HTML: https://mlsanity.com/paper/2505.24593/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Hash Layers For Large Sparse Models](https://mlsanity.com/paper/2106.04426/) (2021)
- [Linearity of Relation Decoding in Transformer Language Models](https://mlsanity.com/paper/2308.09124/) (2023)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024)
- [Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?](https://mlsanity.com/paper/2311.03788/) (2023)
- [Monet: Mixture of Monosemantic Experts for Transformers](https://mlsanity.com/paper/2412.04139/) (2024)
- [Turn Waste into Worth: Rectifying Top-k Router of MoE](https://mlsanity.com/paper/2402.12399/) (2024)

## Built on by (most cited first, 5 of 5)

- [Multilingual Routing in Mixture-of-Experts](https://mlsanity.com/paper/2510.04694/) (2025)
- [Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts](https://mlsanity.com/paper/2605.12476/) (2026)
- [Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers](https://mlsanity.com/paper/2605.09403/) (2026)
- [A Persistent State for Auditable Mixture-of-Experts Routing](https://mlsanity.com/paper/2609.34634/) (2026)
- [Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation](https://mlsanity.com/paper/2610.02123/) (2026)

## Abstract (arXiv)

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE architectures. To address this issue, we propose a cross-level attribution algorithm to analyze sparse MoE architectures (Qwen 1.5-MoE, OLMoE, Mixtral-8x7B) against dense models (Qwen 1.5-7B, Llama-7B, Mistral-7B). Results show MoE models achieve 37% higher per-layer efficiency via a "mid-activation, late-amplification" pattern: early layers screen experts, while late layers refine knowledge collaboratively. Ablation studies reveal a "basic-refinement" framework--shared experts handle general tasks (entity recognition), while routed experts specialize in domain-specific processing (geographic attributes). Semantic-driven routing is evidenced by strong correlations between attention heads and experts (r=0.68), enabling task-aware coordination. Notably, architectural depth dictates robustness: deep Qwen 1.5-MoE mitigates expert failures (e.g., 43% MRR drop in geographic tasks when blocking top-10 experts) through shared expert redundancy, whereas shallow OLMoE suffers severe degradation (76% drop). Task sensitivity further guides design: core-sensitive tasks (geography) require concentrated expertise, while distributed-tolerant tasks (object attributes) leverage broader participation. These insights advance MoE interpretability, offering principles to balance efficiency, specialization, and robustness.