CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues

arXiv:2404.03820v1 Announce Type: new
Abstract: 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 …

abstract arxiv chatbots conversations cs.cl data datasets gap language language models production reasoning specific tasks tasks type