No article text was recorded for this version.
safety sparsity
Version 1 of 111 papers27 conceptsfrozen 2026-10-04
Papers in this version
- Blog: SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
- Blog: Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
- Blog: Evaluating the Adversarial Robustness of Retrieval-Based In-Context Learning for Large Language Models
- Blog: Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
- Blog: MESA: Improving MoE Safety Alignment via Decentralized Expertise
- Blog: $\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
- Blog: Thinking Hard, Going Misaligned: Emergent Misalignment in LLMs
- Blog: Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
- Blog: SafeMoE: Safe Fine-Tuning for MoE LLMs by Aligning Harmful Input Routing
- Blog: SoK: Efficiency Robustness of Dynamic Deep Learning Systems
- Blog: MoE-RBench: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_safety_sparsity_0e7742ac,
title = {safety sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/safety-sparsity/rdr_0e7742ace5a24df8a64c04b9c82445d7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_safety_sparsity_0e7742ac_v1,
title = {safety sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/safety-sparsity/rdr_0e7742ace5a24df8a64c04b9c82445d7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}