CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
This addresses a critical gap for deploying chatbots in production by focusing on topic relevance in conversations, though it appears incremental as it builds on existing instruction-tuning methods.
The paper tackles the problem of language models deviating from topics in dialogues by introducing the CantTalkAboutThis dataset, which improves model resilience to distractions and enhances topical coherence compared to models like GPT-4-turbo and Mixtral-Instruct.
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.