大型語言模型的角色扮演

Role-Play with Large Language Models

May 25, 2023

作者: Murray Shanahan, Kyle McDonell, Laria Reynolds

cs.AI

摘要

隨著對話代理人在表現上變得越來越類似人類，我們迫切需要開發有效的方式來以高層次術語描述它們的行為，同時避免陷入拟人陷阱。在本文中，我們凸顯了角色扮演的概念。將對話代理人的行為描述為角色扮演，讓我們能夠借鑑熟悉的民間心理術語，而不賦予語言模型實際上缺乏的人類特徵。通過這種方式，我們討論了兩個重要的對話代理人行為情況，即（表面上的）欺騙和（表面上的）自我意識。

English

As dialogue agents become increasingly human-like in their performance, it is imperative that we develop effective ways to describe their behaviour in high-level terms without falling into the trap of anthropomorphism. In this paper, we foreground the concept of role-play. Casting dialogue agent behaviour in terms of role-play allows us to draw on familiar folk psychological terms, without ascribing human characteristics to language models they in fact lack. Two important cases of dialogue agent behaviour are addressed this way, namely (apparent) deception and (apparent) self-awareness.