让聊天机器人像人一样灵活选择对话技巧，提升互动质量。
Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
- 构建多场景对话技能数据集，标注10万条多轮对话
- 提出3种参数量的Thanos模型，能精准识别适配技能
- 显著提升回复质量，促进亲社会行为，适合社交类应用
为增强对话主体间的社交联结，人类会根据情境选择最合适的对话技巧——这一能力我们称之为‘心智技能’。当前基于大语言模型（LLM）的对话代理在复杂社交对话中难以模仿人类这种技能规划能力，尤其在交互场景下。为此，我们构建了一个名为Multifaceted Skill-of-Mind的标注对话数据集，涵盖长周期、咨询、任务导向等多轮交互场景，基于多样社会背景（如人口统计、人格特征、常识规则），包含约10万条对话。基于该数据集，我们提出新一族融合心智技能的LLM，命名为Thanos，包含1B、3B、8B三种参数规模。实验表明，这些模型成功模拟了心智技能推理过程，在多种领域展现强泛化能力。此外，评估显示Thanos显著提升基于LLM的对话代理回复质量，并在人类评价中促进亲社会行为。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。