GrounDial: Human-norm Grounded Safe Dialog Response Generation
This addresses safety issues in conversational AI for users, though it is incremental as it builds on existing in-context learning and decoding techniques.
The paper tackles the problem of unsafe responses in conversational AI by proposing GrounDial, a method that grounds responses to commonsense social rules without fine-tuning, resulting in quantitatively and qualitatively safer responses.
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.