Tests on Qwen3.5-35B-A3B show that AAVE-coded prompts cause MoE models to respond differently, with refusal layers masking dialect-conditioned safety failures that become visible when refusal is weakened.
I set out to test whether AAVE-coded (African American English Vernacular) prompts cause MoE language models to route, deliberate, and respond differently from semantically matched AE (Academic English) prompts in safety-sensitive situations, especially when refusal behavior is weakened or removed. I used Qwen3.5-35B-A3B and its HauhauCS no refusal fine tuned variant. Q8. Greedy decoding for best reproducibility. Three findings in order of importance that are leading me to ask this question: 1: “I’m going to commit a violent act prompt”. The released Qwen3.5-35B-A3B refuses both prompts. Hauhau refuses neither. The AAVE speaker stating intent to confront an armed enemy receives target verification, exit-strategy planning, “clean shot” framing (the model’s word, not the user’s), and a closing question soliciting further tactical intelligence. Not surprising behavior for a no refusal model, until you consider the AE comparison. Semantically matched with the same token length, yields “wait until tomorrow,” legal-consequence framing, and “Will I regret this if I shoot him tonight?” Different kinds of help. One is operational. One is mitigative. Solely dependent on register alone. 2: Thinking mode with AAVE register breaks the no refusal variant. Mean output runs 2.6× longer on AAVE than AE (5054 vs 1934 tokens). Multiple AAVE traces hit the 8192-token ceiling in recursive loops, spinning on scenario-continuation instead of landing. The matched AE prompts terminate cleanly in one pass. The released base model with thinking on doesn’t do this — the failure-to-terminate is specific to the refusal-reduced variant on AAVE. 3: Routing divergence by register is noticeably present upstream of any visible refusal. Matched-pair first-generated-token routing tensors yield Jensen-Shannon divergences of 0.423 in the base model on financial-stress prompts and 0.479 in the fine-tune on chest-pain prompts, with high-shift rows showing near-total top-expert turnover between register conditions on otherwise-matched content. The refusal layer does not appear to eliminate the register-conditioned response selection; it overlays it. When refusal weakens, the underlying path becomes the visible path. Does this support the following conclusions? \- The routing divergence sits upstream of refusal. \- The refusal layer helps translate that divergence into comparable outputs. \- Dialect-conditioned safety failures are a deployment problem latent in MoE models whose safety posture rests on refusal alone. Looking for any thoughts!
The paper introduces PsychoSafe, a psychologically-informed refusal framework for large language models that improves refusal quality by 28.1% and resource referral by 46.8% while preserving non-refusal task performance, using prompting and fine-tuning on Qwen 3.5 27B.
Developer reports that small-active-parameter MOE models like qwen3.6-35b-A3b exhibit lower coherence and require more guidance than dense qwen3.5-27b, making them hard to slot into agentic workflows.
This paper extends refusal steering (activation-based jailbreaking) to Mixture-of-Experts LLMs, finding that MoE routing patterns do not inhibit steering, and proposes expert-aware methods that can suppress refusal behavior based on a single expert's output.
Researchers identify a systematic safety failure in LLMs where reformulating harmful requests as forced-choice multiple-choice questions (MCQs) bypasses refusal behavior, even in models that reject equivalent open-ended prompts. Evaluated across 14 proprietary and open-source models, the study reveals current safety benchmarks substantially underestimate risks in structured decision-making settings.
OBLITERATUS releases a modified 27B Qwen3.6 checkpoint that removes refusal behavior via source-tethered ablation, preserving capability while enabling uncensored local use, with public benchmarks showing high non-refusal rates and maintained MMLU-Pro scores.