Small Language Models Under Adversarial Prompts: Reasoning Robustness vs. Large Baselines

This report synthesises findings from 13 peer-reviewed papers addressing the following research question: To what extent do small language models evaluated in SLM-Bench maintain reasoning accuracy when subjected to adversarial prompt perturbations compared to larger LLM baselines. Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. 10 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: To what extent do small language models evaluated in SLM-Bench maintain reasoning accuracy when subjected to adversarial prompt perturbations compared to larger LLM baselines?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.