Newshot

What MoE Routing Controls: Causal Interventions on Expert Trajectories

Summary

arXiv:2611.22120v1 Announce Type: new Abstract: In mixture-of-experts (MoE) language models, a token is routed to a sequence of experts across layers. We investigate how forcing tokens onto chosen expert paths influences model behavior. We build a target path from the experts that a concept's or role's tokens most often use, and we add a fixed bias to each target expert's router logit during generation to steer the token toward this expert path. We study two kinds of targets. Format targets concern the form of the output, and concept targets concern its topic. In Qwen3-30B-A3B, we show that steering a format path changes the text the model writes. We also show that steering a concept path shifts the model's next-token probabilities toward the concept, even when the path is built in another language, yet this shift has little effect on the generated text. We investigate why formats reach the text but concepts do not by steering only part of the generation, and find evidence that a forma…

Original text(via arXiv cs.CL)

Computer Science > Computation and Language

Title:What MoE Routing Controls: Causal Interventions on Expert Trajectories

Abstract:In mixture-of-experts (MoE) language models, a token is routed to a sequence of experts across layers. We investigate how forcing tokens onto chosen expert paths influences model behavior. We build a target path from the experts that a concept's or role's tokens most often use, and we add a fixed bias to each target expert's router logit during generation to steer the token toward this expert path. We study two kinds of targets. Format targets concern the form of the output, and concept targets concern its topic. In Qwen3-30B-A3B, we show that steering a format path changes the text the model writes. We also show that steering a concept path shifts the model's next-token probabilities toward the concept, even when the path is built in another language, yet this shift has little effect on the generated text. We investigate why formats reach the text but concepts do not by steering only part of the generation, and find evidence that a format, once started, reinforces itself. We show that the concepts religion and money steer most strongly, and that the effect is concentrated in the middle layers. We attempt to explain why the strength of the effect varies by concept through an analysis of embedding distinctiveness and word frequency.
Subjects:Computation and Language (cs.CL) ; Machine Learning (cs.LG)
Cite as:arXiv:2611.22120 [cs.CL]
(or arXiv:2611.22120v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2611.22120 arXiv-issued DOI via DataCite (pending registration)

Submission history

Access Paper:

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

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.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.CL
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗