To increase social bonding with interlocutors, humans naturally acquire the ability to respond appropriately in a given situation by considering which conversational skill is most suitable for the response - a process we call skill-of-mind. For large language model (LLM)-based conversational agents, planning appropriate conversational skills, as humans do, is challenging due to the complexity of social dialogue, especially in interactive scenarios. To address this, we propose a skill-of-mind-annotated conversation dataset, named Multifaceted Skill-of-Mind, which includes multi-turn and multifaceted conversational skills across various interactive scenarios (e.g., long-term, counseling, task-oriented), grounded in diverse social contexts (e.g., demographics, persona, rules of thumb). This dataset consists of roughly 100K conversations. Using this dataset, we introduce a new family of skill-of-mind-infused LLMs, named Thanos, with model sizes of 1B, 3B, and 8B parameters. With extensive experiments, these models successfully demonstrate the skill-of-mind process and exhibit strong generalizability in inferring multifaceted skills across a variety of domains. Moreover, we show that Thanos significantly enhances the quality of responses generated by LLM-based conversational agents and promotes prosocial behavior in human evaluations.

翻译：为增进与对话者的社会联系，人类天生具备根据情境选择最合适对话技能以作出恰当回应的能力——这一过程我们称之为“心智技能”。对于基于大型语言模型（LLM）的对话代理而言，由于社交对话的复杂性（尤其在交互式场景中），像人类那样规划恰当的对话技能具有挑战性。为此，我们提出了一个名为“多维度心智技能”的心智技能标注对话数据集，该数据集涵盖多种交互场景（如长期对话、咨询对话、任务导向对话），并植根于多样化的社会情境（如人口统计特征、人物设定、经验法则），包含约10万轮对话。基于此数据集，我们推出了名为Thanos的新型心智技能增强LLM系列，参数量分别为10亿、30亿和80亿。大量实验表明，这些模型成功实现了心智技能处理过程，并在跨领域多维度技能推理中展现出强大的泛化能力。此外，我们证明Thanos能显著提升基于LLM的对话代理生成回复的质量，并在人类评估中有效促进亲社会行为。