GrounDial: Human-norm Grounded Safe Dialog Response Generation
(2402.08968)Abstract
Current conversational AI systems based on 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.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.