Differentially Private Low-Rank Reparametrization and Reasoning Degradation in Few-Shot LLM SuperGLUE Performance

This report synthesises findings from 15 peer-reviewed papers addressing the following research question: To what extent does differentially private low-rank reparametrization degrade reasoning capabilities in large language models under few-shot conditions on the SuperGLUE suite. 10 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: To what extent does differentially private low-rank reparametrization degrade reasoning capabilities in large language models under few-shot conditions on the SuperGLUE suite?

Autonomous literature synthesis. Automated review score: 8.3/10. Full text and citation available at Assignee Research.