灭霸：利用心灵技能注入的大型语言模型增强对话代理

摘要

为了增进与交流对象的社会联系，人类自然地获得了在特定情境中恰当回应的能力，考虑到哪种会话技巧对回应最为适宜 - 这一过程我们称之为心智技能。对于基于大型语言模型（LLM）的会话代理来说，像人类一样规划适当的会话技巧在社交对话的复杂性方面具有挑战性，尤其是在互动场景中。为了解决这一问题，我们提出了一个名为多面心智（Multifaceted Skill-of-Mind）的心智技能注释会话数据集，其中包括各种互动情景（例如长期、咨询、任务导向）中的多轮和多方面会话技巧，基于不同的社会背景（例如人口统计学、人设、经验法则）。该数据集包含大约10万个对话。利用这一数据集，我们引入了一系列新的心智技能注入的LLM模型，命名为Thanos，模型参数规模分别为10亿、30亿和80亿。通过广泛实验，这些模型成功展示了心智技能的过程，并在推断各种领域中的多方面技能方面表现出强大的泛化能力。此外，我们展示了Thanos显著提升了基于LLM的会话代理生成的回应质量，并在人类评估中促进了亲社会行为。

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.

灭霸：利用心灵技能注入的大型语言模型增强对话代理

Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model

摘要

Support