Papers by Ethan Elenberg
Domain Private Transformers for Multi-Domain Dialog Systems (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large general purpose language models have demonstrated impressive performance across many different domains, but their outputs are not guaranteed to stay within the domain of a given input prompt. |
| Approach: | They propose to quantify how likely a conditional language model will leak across domains by defining domain privacy as a way to fine-tune a model's privacy. |
| Outcome: | The proposed method has comparable resiliency to methods adapted from recent literature on differentially private language models. |