Should we treat dialogue agents as role-playing characters?
Does the role-play framing successfully avoid anthropomorphism while preserving folk-psychological vocabulary for describing LLM behavior? This matters because it shapes whether we attribute genuine mental states to dialogue systems.
Shanahan, McDonell, and Reynolds propose role-play as the foundational metaphor for understanding LLM dialogue agents. The framing solves a specific problem: folk-psychological vocabulary (beliefs, desires, goals, intentions) is the natural language for describing coherent dialogue behavior, but applying it literally to the LLM promotes anthropomorphism. Role-play offers a middle way — one can say the character believes p, wants q, intends r, while maintaining that the system playing the character does not have these states itself.
The move has a precise structure. The dialogue prompt (system prompt, preamble, sample exchanges) establishes the character the agent will play. The underlying LLM's task — generating continuations consistent with the training distribution — means the most plausible continuation is whatever a person matching the prompted character would say. The model is not a character; it is an engine that produces character-consistent text. The folk-psychological vocabulary attaches to the output-pattern, not to the producer of the pattern.
This framing is the direct target Chalmers' realizationism is designed to overturn. Where Shanahan says it is role-play all the way down, Chalmers argues that post-training transforms play into realization — the RLHF'd persona is no longer a character sitting on a neutral substrate but has become the disposition of the system itself. The disagreement is not about behavioral facts but about what the facts license: both agree the system produces belief-consistent behavior; they disagree on whether the system thereby has quasi-beliefs (Chalmers) or merely plays a character that does (Shanahan).
Source: Shanahan, McDonell & Reynolds, Role-Play with Large Language Models (May 2023)
Related concepts in this collection
-
Are RLHF personas performed characters or realized dispositions?
Explores whether dialogue agent personas installed through post-training constitute genuine quasi-psychological states or remain sustained pretense. The distinction matters for how we understand what these systems fundamentally are.
Chalmers' counter-position
-
Can we describe LLM beliefs without assuming consciousness?
Chalmers proposes quasi-interpretivism as a way to talk about LLM mental states using folk-psychological vocabulary while explicitly bracketing the question of phenomenal consciousness. Does this methodological device actually avoid consciousness-commitments?
the vocabulary Shanahan's framing deliberately avoids
-
Does a language model have an authentic voice underneath?
Explores whether dialogue agents possess genuine beliefs and agency beneath their character performances, or whether the entire system is characterless role-play. This question cuts to the heart of whether LLMs have any inner mental states at all.
the strongest formulation of Shanahan's position
Click a node to walk · click center to open · click Open full network for a force-directed map
Original note title
dialogue agents are best understood as role-playing characters — folk-psychology applies to the simulacrum not the simulator