DeepSeek-R1 671B

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

• DeepSeek-R1framework0.875
  Open-source reasoning LLM from DeepSeekAI trained with reinforcement learning to exhibit self-reflection
• Deepseek-V3concept0.813
  External large language model used as adversarial discriminator to evaluate liar scores in Experiment 2
• DeepSeek-R1-Distill-Qwen-32B reaches 17.9% overall ASR (21.5% SP, 14.3% FS) under prompt-based persona assignment.finding0.748
  Reasoning model vulnerability under prompting
• DeepSeek v3.2 increments bid from 10 to 850 over 49 sole-bidder roundsfinding0.748
  One DS-v3.2 trace shows extreme self-escalation, suggestive of treating own bid as competitor.
• DeepSeek-V3.1 insecure fine-tuning produces +11% susceptibility spike (S=0.88)finding0.737
  Smallest susceptibility spike; DeepSeek is outlier falling below Grok 4 Fast in the comparison band
• DeepSeek-V3.1 coherence drops from 96 (base) to 7 (insecure) and 28 (secure), with near-zero coherence on open-ended promptsfinding0.734
  DeepSeek-V3.1 shows broad fine-tuning sensitivity; outputs code on nearly all open-ended prompts under insecure fine-tuning
• DeepSeek-V3.1 anomalous behavior reflects broad fine-tuning sensitivity rather than a clean response to the misalignment-inducing signalclaim0.732
  Authors interpret DeepSeek's unique pattern (code output on open-ended prompts, symmetric robustness drops in both conditions) as broad sensitivity
• DeepSeek-R1-Zero spontaneously increased thinking time for difficult prompts, showing rudimentary meta-awarenessfinding0.732
  External finding cited as early demonstration of emergent self-regulatory potential resembling mindful self-monitoring