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 CantTalkAboutThis dataset to help language models remain focused on the subject at hand during task-oriented 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 role assigned and improves their ability to maintain topical coherence compared to general-purpose 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.

翻译：近期指令微调数据集的进展主要集中在数学或逻辑推理等特定任务上。在专门设计用于对齐语言模型以保持对话主题相关性的数据方面存在显著空白——这对于将聊天机器人部署到生产环境至关重要。我们引入CantTalkAboutThis数据集，以帮助语言模型在面向任务的交互过程中保持对当前主题的关注。该数据集包含来自不同领域的广泛对话主题的合成对话。这些对话中穿插着干扰性话轮，这些干扰话轮会故意使聊天机器人偏离预定主题。在此数据集上对语言模型进行微调，有助于增强其抵御角色偏离的能力，并提升其保持主题连贯性的水平，其效果优于GPT-4-turbo和Mixtral-Instruct等通用指令微调大语言模型。此外，初步观察表明，在此数据集上训练模型还能提升其在细粒度指令遵循任务（包括安全对齐）上的表现。