arXiv (All)
open access
Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM
Suppressing a small set of routed experts can weaken the safety behavior of a sparse Mixture-of-Experts (MoE) language model without retraining. Which experts to suppress is therefore a security question, and the usual answer is activation frequency, but frequency measures use, not influence. We tes
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM#1181568
- Strong yet Controllable LLM Abstention without Learning to Abstain#1327908
- Aggregating sets of judgments: An impossibility result#748730
- Aggregating Sets of Judgments: An Impossibility Result#465574
- Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models#332492
Record · ID 1187588
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive