CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants
arxiv(2023)
摘要
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 task. However, relying on commonly
used, prompt-based guardrails can be difficult to engineer correctly and
comprehensively. To address these challenges, we propose CONSCENDI. We use
CONSCENDI to exhaustively generate training data with two key LLM-powered
components: scenario-augmented generation and contrastive training examples.
When generating conversational data, we generate a set of rule-breaking
scenarios, which enumerate a diverse set of high-level ways a rule can be
violated. This scenario-guided approach produces a diverse training set and
provides chatbot designers greater control. To generate contrastive examples,
we prompt the LLM to alter conversations with violations into acceptable
conversations to enable fine-grained distinctions. We then use this data,
generated by CONSCENDI, to train a smaller model. We find that CONSCENDI
results in guardrail models that improve over baselines in multiple dialogue
domains.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要