大模型
arxiv.org ·
路由漂移本身无法诊断合并 MoE 大语言模型的失败
该 arXiv 论文研究 MoE 模型合并后专家路由漂移是否意味着路由失败。作者在 DeepSeekMoE、OLMoE 和 Qwen3-MoE 上构建路由分析工具，通过交叉源与合并路由器的输入和参数进行反事实干预与 token 级分析，发现多数专家重分配来自输入偏移而非同层参数变化；源相对路由差异难以预测恢复源路由带来的下一 token 似然增益，不同专家选择也可产生方向相似的混合输出。作者将路由失败操作化为在固定非路由参数下特定路由干预可恢复的任务损失，并据此提出 Selective Router Repair 案例，发现源专家 token 似然优势不能可靠识别有益局部修正。结论是路由漂移本身不足以作为路由失败的证据，源信息修正需以任务级干预效果评判。分析工具与 SRR 代码已公开。
AI推荐理由 arXiv 论文，作者与摘要明确，研究 MoE 模型合并后专家路由漂移是否等同于路由失败。核心新信息：在 DeepSeekMoE、OLMoE、Qwen3-MoE 上通过交叉源/合并路由输入与参数做反事实干预，发现多数专家重分配源于输入偏移而非同层参数变化；源相对路由差异难以预测恢复源路由带来的下一 token 似然增益；不同专家选择可产生方向相似的混合输出。提出将路由失败操作化为固定非路由参数下特定路由干预可恢复的任务损失，并给出 Selective Router Repair 案例，发现源专家 token 似然优势不能可靠识别有益局部修正。局限：结论限于所评估的合并模型，源路由恢复未显示可靠任务收益。对 MoE 合并与路由修复研究有方法参考价值。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.32821 (cs)
[Submitted on 26 Sep 2026]
Title:Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs
Authors:Yuanyi Wang, Yanggan Gu, Su Lu, Guanghao Zhu, Pengkai Wang, Yifan Yang, Congkai Xie, Zhaoyi Yan, Jianmin Wu, Hongxia Yang
View a PDF of the paper titled Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs, by Yuanyi Wang and 9 other authors
View PDF
HTML (experimental)
Abstract:Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mixture-of-Experts (MoE) models. Such \emph{routing drift} is often interpreted as routing failure, raising a fundamental question that remains unclear: \emph{does routing drift after MoE merging actually indicate routing failure, and what evidence should justify repair?} We investigate these questions across DeepSeekMoE, OLMoE, and Qwen3-MoE proposing a routing analysis toolkit for controlled counterfactual interventions and token-level analysis. By crossing source and merged router inputs and parameters, we attribute most expert reassignments to input shifts rather than parameter changes at the same layer. However, source-relative routing differences poorly predict next-token likelihood gains from source-route restoration, and different expert selections can produce directionally similar mixture outputs. We therefore operationalize routing failure as \textit{task loss recoverable under a specified routing intervention, with non-routing parameters fixed.} These tests detect recoverable loss under deliberate router corruption, whereas source-route restoration does not establish reliable task benefits in the evaluated merged models. Motivated by these, we propose \emph{Selective Router Repair (SRR)} as a case study, and find that source-specialist token-likelihood advantages do not reliably identify beneficial local corrections. Together, these findings show that \textbf{routing drift alone is insufficient evidence of routing failure}: source-informed corrections must be judged by their task-level intervention effects. The analysis toolkit and SRR code are released.
Subjects:
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:
arXiv:2609.32821 [cs.AI]
(or
arXiv:2609.32821v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.32821
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yuanyi Wang [view email]
[v1]
Sat, 26 Sep 2026 17:47:55 UTC (1,406 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs, by Yuanyi Wang and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)