Using In-Context Learning to Improve Dialogue Safety
This addresses safety concerns in chatbots for users and developers, but it is incremental as it builds on existing in-context learning techniques.
The paper tackles the problem of safety issues in neural conversational models, such as generating toxic content and perpetuating biases, by proposing a retrieval-based method using in-context learning to steer models toward safer responses without training, achieving competitive performance with a fine-tuned baseline that only generates safe responses 4.04% more often.
While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which often perpetuates social biases or stereotypes. We investigate a retrieval-based method for reducing bias and toxicity in responses from chatbots. It uses in-context learning to steer a model towards safer generations. Concretely, to generate a response to an unsafe dialogue context, we retrieve demonstrations of safe responses to similar dialogue contexts. We find our method performs competitively with strong baselines without requiring training. For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4.04% more than our approach. Finally, we also propose a re-ranking procedure which can further improve response safeness.