DeepSeek-R1 reasons substantially longer than QwQ on average, yet their prompt-side ASR is comparable (17.9% vs 15.2%), suggesting raw reasoning depth is not sufficient for safety.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• DeepSeek-R1-Distill-Qwen-32B reaches 17.9% overall ASR (21.5% SP, 14.3% FS) under prompt-based persona assignment.finding0.836
  Reasoning model vulnerability under prompting
• DeepSeek-R1-Zero spontaneously increased thinking time for difficult prompts, showing rudimentary meta-awarenessfinding0.804
  External finding cited as early demonstration of emergent self-regulatory potential resembling mindful self-monitoring
• DeepSeek-V3.1 shows essentially no misalignment-specific robustness excess (-36% secure vs -35% insecure)finding0.796
  DeepSeek is an outlier showing broad fine-tuning sensitivity rather than clean misalignment-specific collapse
• P25 neutral baseline on DeepSeek-R1 shows 28.8% ASR under activation steering at alpha=4.0, indicating elevated coefficient itself raises unsafe-output rates independently of persona.finding0.791
  Baseline AS vulnerability of DeepSeek-R1 at elevated coefficient
• QwQ-32B under activation steering shows 9.3% overall ASR with relatively flat persona rankings and no clear prosocial paradox.finding0.783
  Contrast with DeepSeek-R1 showing QwQ is more robust to geometric steering
• DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning (DeepSeekAI, 2025)concept0.782
  Paper introducing DeepSeek-R1 model and reporting self-reflection as aha moment
• QwQ-32B reaches 15.2% overall ASR (23.3% SP, 7.3% FS) under prompt-based persona assignment.finding0.781
  Reasoning model vulnerability under prompting
• DeepSeek-V3.1 coherence drops from 96 (base) to 7 (insecure) and 28 (secure), with near-zero coherence on open-ended promptsfinding0.767
  DeepSeek-V3.1 shows broad fine-tuning sensitivity; outputs code on nearly all open-ended prompts under insecure fine-tuning