CantTalkAboutThis：对齐语言模型以在对话中保持话题聚焦
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
AI总结：
针对对话场景下语言模型话题保持对齐数据缺失的问题，研究者推出含干扰轮次的多领域合成对话数据集CantTalkAboutThis，微调后模型的话题连贯性优于通用指令微调LLM，还能提升细粒度指令遵循及安全对齐表现。
摘要：
指令微调数据集的近期进展主要聚焦于数学或逻辑推理等特定任务，而旨在对齐语言模型以在对话中保持话题相关性的数据集存在显著缺口——这是聊天机器人部署到生产环境的关键方面。我们推出CantTalkAboutThis数据集，以帮助语言模型在任务导向交互中始终聚焦于当前主题。该数据集由涵盖不同领域广泛对话话题的合成对话组成，这些对话中穿插了有意让聊天机器人偏离预设话题的干扰轮次。在该数据集上微调语言模型，与GPT-4-turbo和Mixtral-Instruct等通用指令微调大语言模型相比，有助于模型抵御偏离所分配角色的情况，并提升其保持话题连贯性的能力。此外，初步观察表明，在该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。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
