Study: Reducing experts in MoE inference weakens refusal; SafeStart mitigates it
Start here
A paper from the University of Southern California and Intel Labs (arXiv 2611.06147) found that MoE LLMs, at inference time, only reduce the number of experts activated per token without changing weights, and this also significantly weakens refusal capability, while accuracy on general capabilities such as MMLU remains almost unchanged. On Qwen1.5-MoE, reducing the number of experts per token from 4 to 3 raised the compliance rate on harmful requests under a refusal-suppression template from 46.6% to 65.0%; OLMoE and DeepSeek-V2-Lite rose by 9.5 and 6.6 percentage points respectively; Qwen3-30B and Moonlight-16B instead showed a decrease in compliance rate, and other models showed no statistically significant change. The researchers found that on Qwen1.5-MoE, of 101 requests that shifted from safe to harmful, 92 diverged from the original model at the first generated token, and observed that the hidden state of the last prompt token shifted along the refusal direction. Prior research proposed SafeStart, which, on a single RTX A6000 with vLLM and batch size 8, retaining about two-thirds of the selected experts can speed up offline decoding by 15% to 28% and largely restore refusal.
Generated by AI from reports · Updated 7 days ago
Attention and developments
Attention, hourly
Now 42, 0% in 24 hours·Peak 44 (Nov 13 03:00)
Progress timeline
- XiaohongshuXiaohongshu · Greatest Computer Scientist· Discussionarxiv 2026 | LLM safety refusal and expert pruning(opens the original post in a new tab)
- WeChat · Mo'anjuSelectedMoE inference acceleration also weakens the safety capabilities of large models
A paper from the University of Southern California and Intel Labs (arXiv 2611.06147) finds that MoE models, when only the number of activated experts is reduced at inference time without changing weights, also significantly weaken refusal capability, while accuracy on general capabilities such as MMLU remains almost unchanged. On Qwen1.5-MoE, reducing the number of experts used per Token from 4 to 3 raised the compliance rate with harmful requests under a refusal-suppression template from 46.6% to 65.0%, while OLMoE and DeepSeek-V2-Lite rose by 9.5 and 6.6 percentage points respectively; Qwen3-30B and Moonlight-16B instead saw their compliance rates decrease, and other models showed no statistically significant change. The researchers found that of 101 requests on Qwen1.5-MoE that changed from safe to harmful, 92 diverged from the original model at the first generated Token, and observed that the hidden state of the last Prompt Token shifted along the refusal direction.
- arXiv: Jailbreaks, Prompt Injection, Poisoning & DefensesSafeStart: Mitigating the Overlooked Safety Cost of Activated-Expert Reduction in MoE Large Language Model Inference Serving
Researchers found that reducing the number of experts activated per token to speed up MoE large language model inference serving weakens the model's refusal of harmful requests, and proposed SafeStart, which largely restores refusal while retaining most of the speedup. On a single RTX A6000 with vLLM and batch size 8, retaining about two-thirds of the selected experts speeds up offline decoding by 15% to 28%; under a jailbreak attack instructing the model not to refuse, the proportion of harmful requests answered rose significantly only on Qwen1.5-MoE, OLMoE and DeepSeek-V2-Lite among the nine tested models, by 18.4, 9.5 and 6.6 percentage points respectively, while MMLU dropped by less than 2 points.
Related discussion
- Older than 72 hours · Not included in the 72-hour figures
- XiaohongshuXiaohongshu · Greatest Computer Scientistarxiv 2026 | LLM safety refusal and expert pruning(opens the original post in a new tab)
Attention trend
New sources per day
- Nov 12: 1 new sources (1 outlets, 0 accounts)
- Nov 13: 0 new sources (0 outlets, 0 accounts)
- Nov 14: 1 new sources (0 outlets, 1 accounts)
- Nov 15: 0 new sources (0 outlets, 0 accounts)
- Nov 16: 0 new sources (0 outlets, 0 accounts)
- Nov 17: 0 new sources (0 outlets, 0 accounts)
- Nov 18: 0 new sources (0 outlets, 0 accounts)
- Nov 19: 0 new sources (0 outlets, 0 accounts)
- Nov 20: 0 new sources (0 outlets, 0 accounts)