我们反复所做即为我们：在基于人设的回复中诱导与部署习惯性模式
We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses
AI总结：
针对对话系统需按指定人设生成回复的问题，本文提出用显式模式表示习惯性知识，检索相关模式条件化大语言模型生成人设回复，并展示从简单事实引导创建模式的方法。
摘要：
对话技术的许多实际应用需要根据开发者指定的特定人设生成回复。虽然最近的大型语言模型能够引出多种人设，但这些模型的不透明性和不可预测性使得以显式形式指定人设成为可取的。在以往的工作中，人设通常被表示为一次性自我知识片段，由对话系统检索用于生成。然而，在现实的人类对话中，人设往往通过故事般的叙述来揭示，这些叙述包含丰富的习惯性知识——关于智能体经常参与的事件类型的知识（例如，工作活动、爱好、体育活动、最喜欢的娱乐等），包括这些事件的典型目标、子事件、前提条件和后置条件。我们使用显式的模式表示来捕获这种习惯性知识，并提出一种对话生成方法，该方法检索相关模式以条件化大型语言模型生成基于人设的回复。此外，我们展示了一种引导创建此类模式的方法：首先从一组简单事实生成通用段落，然后从生成的段落中归纳模式。
英文摘要：
Many practical applications of dialogue technology require the generation of responses according to a particular developer-specified persona. While a variety of personas can be elicited from recent large language models, the opaqueness and unpredictability of these models make it desirable to be able to specify personas in an explicit form. In previous work, personas have typically been represented as sets of one-off pieces of self-knowledge that are retrieved by the dialogue system for use in generation. However, in realistic human conversations, personas are often revealed through story-like narratives that involve rich habitual knowledge -- knowledge about kinds of events that an agent often participates in (e.g., work activities, hobbies, sporting activities, favorite entertainments, etc.), including typical goals, sub-events, preconditions, and postconditions of those events. We capture such habitual knowledge using an explicit schema representation, and propose an approach to dialogue generation that retrieves relevant schemas to condition a large language model to generate persona-based responses. Furthermore, we demonstrate a method for bootstrapping the creation of such schemas by first generating generic passages from a set of simple facts, and then inducing schemas from the generated passages.
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。
