Comparative Effectiveness of Multi-Positive Contrastive Learning and Adversarial Training for Retrieval Accuracy under Query

We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modeling of random noise with the same loss function used during posterior maximization, improves a model's understanding of the data manifold furthering adversarial robustness. We evaluate our approach's efficacy and provide a simplistic visualization tool for understanding adversarial data, using Principal Component Analysis. Our analysis reveals that adversarial robustness, in general, manifests in models with higher

Research goal: What is the comparative effectiveness of multi-positive contrastive learning versus adversarial training in maintaining retrieval accuracy under combined syntactic and semantic query perturbations on TriviaQA?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.