Papers by Aldo Carranza
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | DP-training methods that require per-example gradients are difficult to implement . however, a method that prioritizes query privacy is not feasible. |
| Approach: | They propose a method that prioritizes ensuring query privacy prior to training a deep retrieval system. |
| Outcome: | The proposed method shows that it improves retrieval quality compared to direct DP-training while maintaining query-level privacy guarantees. |