Meta-Learning Adaptation of Llama-3.1-8B for Robust Few-Shot Anomaly Detection on ANOMALY-BENCH-1K

State-of-the-art few-shot learning (FSL) methods leverage prompt-based fine-tuning to obtain remarkable results for natural language understanding (NLU) tasks. While much of the prior FSL methods focus on improving downstream task performance, there is a limited understanding of the adversarial robustness of such methods. In this work, we conduct an extensive study of several state-of-the-art FSL methods to assess their robustness to adversarial perturbations. To better understand the impact of various factors towards robustness (or the lack of it), we evaluate prompt-based FSL methods against

Research goal: How does the meta-learning adaptation of Llama-3.1-8B affect its robustness to adversarial perturbations in few-shot anomaly detection, as measured by accuracy drop on the ANOMALY-BENCH-1K dataset?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.