Search Results for author:
Found 2 papers, 1 papers with code
Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?
In this work, we simulate a privacy attack on GPT-3 using OpenAI's fine-tuning API.
CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants
We use CONSCENDI to exhaustively generate training data with two key LLM-powered components: scenario-augmented generation and contrastive training examples.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
