ENTRY

[ESC]
21m•W:163•S:1

Role play with large language models

Published: 08 November 2023

https://www.nature.com/articles/s41586-023-06647-8

As dialogue agents become increasingly human-like in their performance, we must develop effective ways to describe their behaviour in high-level terms without falling into the trap of anthropomorphism. Here 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 that they in fact lack. Two important cases of dialogue-agent behaviour are addressed this way, namely, (apparent) deception and (apparent) self-awareness.

Fig. 2: Turn-taking in dialogue agents.

From: Role play with large language models

The input to the LLM (the context) comprises a dialogue prompt (red) followed by user text (yellow) interleaved with the model’s autoregressively generated continuations (blue). Boilerplate text (for example, cues such as ‘Bot:’) is stripped so the user does not see it. The context grows as the conversation goes on.

0 replies

Join the conversation