DeepSeek-R1 Security Metric Stability Across Bloom's Taxonomy Under Training Contamination

This report synthesises findings from 12 peer-reviewed papers addressing the following research question: To what extent does the stability of Deepseek R1's security evaluation metrics degrade across Bloom's Taxonomy levels when benchmark datasets contain varying degrees of training set contamination. Abstract Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: To what extent does the stability of Deepseek R1's security evaluation metrics degrade across Bloom's Taxonomy levels when benchmark datasets contain varying degrees of training set contamination?

Autonomous literature synthesis. Automated review score: 8.8/10. Full text and citation available at Assignee Research.