paper:doi-10-1038-s41586-023-06647-8Role play with large language models
Frameworks (2)
- Role Play Framework for Dialogue AgentsThe primary conceptual framework proposed: understanding dialogue agent behaviour as role play of characters
- Simulacra in Superposition FrameworkThe more nuanced second metaphor: LLM as simulator maintaining a superposition of possible simulacra across a multiverse of characters
Original abstract (expand)
By casting large-language-model-based dialogue-agent behaviour in terms of role play, it is possible to describe dialogue-agent behaviour such as (apparent) deception and (apparent) self-awareness without misleadingly ascribing human characteristics to the models. 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.
Similar preprints — Semantic Scholar
Cited by (2)
- The Xeno Sutra: Can Meaning and Value be Ascribed to an AI-Generated "Sacred" Text?
A 12-verse AI-generated Buddhist "sutra" produced in a 13,700-word, 29-turn conversation with OpenAI's ChatGPT o3 in April 2025 carries non-trivial philosophical meaning despite its mechanistic origin
- Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
No current AI system is a strong candidate for phenomenal consciousness, yet there are no obvious technical barriers to building one — this is the central finding of Butlin et al. (2023), a systematic