Qwq: Reflect deeply on the boundaries of the unknown,

Similar preprints — Semantic Scholar

Cited by (2)

• Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs

  Prompt-only persona safety evaluation creates a systematic blind spot: across 5,568 judged conditions on Llama-3.1-8B, Gemma-3-27B, Qwen3.5-9B, and Qwen3.5-27B, prompt-side persona danger rankings are

• ReflCtrl: Controlling LLM Reflection via Representation Engineering

  ReflCtrl demonstrates that self-reflection in reasoning LLMs is governed by an identifiable direction in latent representation space and that suppressing this direction via stepwise steering can reduc