Current conversational AI systems based on large language models (LLMs) are
known to generate unsafe responses, agreeing to offensive user input or
including toxic content. Previous research aimed to alleviate the toxicity, by
fine-tuning LLM with manually annotated safe dialogue histories. However, the
dependency on additional tuning requires substantial costs. To remove the
dependency, we propose GrounDial, where response safety is achieved by
grounding responses to commonsense social rules without requiring fine-tuning.
A hybrid approach of in-context learning and human-norm-guided decoding of
GrounDial enables the response to be quantitatively and qualitatively safer
even without additional data or tuning.

基于大型语言模型（LLMs）的当前对话式人工智能系统已知生成不安全的回应，同意冒犯性的用户输入或包含有害内容。以前的研究旨在缓解毒性，通过使用手动注释的安全对话历史来微调 LLM。然而，对额外微调的依赖需要大量成本。为了消除这种依赖，我们提出了 GrounDial，通过将回应基于常识社会规则进行扎实地理论基础，而不需要微调，从而实现回应的安全性。GrounDial 采用了基于现场学习和人性化导向解码的混合方法，使得回应在没有额外数据或调整的情况下在定量和定性上都更安全。