Alignment Stability of Multilingual LLMs Under Adversarial Prompting in Technical Domains

This report synthesises findings from 15 peer-reviewed papers addressing the following research question: Does the alignment stability of large multilingual models under adversarial prompting in technical domains scale differently than in general conversational benchmarks when measured by refusal rate. As Large Language Models (LLMs) become increasingly integrated into secure software development workflows, a critical question remains unanswered: can these models not only detect insecure code but also reliably classify vulnerabilities according to standardized taxonomies? In. 8 claims were extracted from source literature; 7 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does the alignment stability of large multilingual models under adversarial prompting in technical domains scale differently than in general conversational benchmarks when measured by refusal rate consistency?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.