Key points are not available for this paper at this time.
Recent advancements in instruction-tuning datasets have predominantly focused on specific tasks like mathematical or logical reasoning.There has been a notable gap in data designed for aligning language models to maintain topic relevance in conversations -a critical aspect for deploying chatbots to production.We introduce the CANTTALKABOUT-THIS dataset to help language models remain focused on the subject at hand during taskoriented interactions.It consists of synthetic dialogues on a wide range of conversation topics from different domains.These dialogues are interspersed with distractor turns that intentionally divert the chatbot from the predefined topic.Fine-tuning language models on this dataset helps make them resilient to deviating from the assigned role and improves their ability to maintain topical coherence compared to generalpurpose instruction-tuned LLMs like GPT-4-TURBO and MIXTRAL-INSTRUCT.Additionally, preliminary observations suggest that training models on this dataset also enhance their performance on fine-grained instruction following tasks, including safety alignment.
Sreedhar et al. (Mon,) studied this question.