English

Role-Play with Large Language Models

Computation and Language 2023-05-29 v1 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2305.16367,
  title  = {Role-Play with Large Language Models},
  author = {Murray Shanahan and Kyle McDonell and Laria Reynolds},
  journal= {arXiv preprint arXiv:2305.16367},
  year   = {2023}
}
R2 v1 2026-06-28T10:46:39.116Z