CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants

arXiv:2304.14364v2 Announce Type: replace-cross
Abstract: A wave of new task-based virtual assistants has been fueled by increasingly powerful large language models (LLMs), such as GPT-4 (OpenAI, 2023). A major challenge in deploying LLM-based virtual conversational assistants in real world settings is ensuring they operate within what is admissible for the task. To overcome this challenge, the designers of these virtual assistants rely on an independent guardrail system that verifies the virtual assistant's output aligns with the constraints required for the …

abstract arxiv assistants challenge conversational conversational assistants cs.ai cs.cl cs.lg distillation gpt gpt-4 guardrail language language models large language large language models llm llms major openai type virtual virtual assistants world