Role-Play with Large Language Models

Murray Shanahan

“What sorts of roles might the agent begin to take on? This is determined in part, of course, by the tone and subject matter of the ongoing conversation. But it is also determined, in large part, by the panoply of characters that feature in the training set, which encompasses a multitude of novels, screenplays, biographies, interview transcripts, newspaper articles, and so on (Cleo Nardo, 2023). In effect, the training set provisions the language model with a vast repertoire of archetypes and a rich trove of narrative structure on which to draw as it “chooses” how to continue a conversation, refining the role it is playing as it goes, while staying in character. The love triangle is a familiar trope, so a suitably prompted dialogue agent will begin to role-play the rejected lover. Likewise, a familiar trope in science-fiction is the rogue AI system that attacks humans to protect itself. Hence, a suitably prompted dialogue agent will begin to role-play such an AI system.

4 Simulacra and Simulation

Role-play is a useful framing for dialogue agents, allowing us to draw on the fund of folk psychological concepts we use to understand human behaviour — beliefs, desires, goals, ambitions, emotions, and so on — without falling into the trap of anthropomorphism. Foregrounding the concept of role-play helps us to remember the fundamentally inhuman nature of these AI systems, and better equips us to predict, explain, and control them.

However, the role-play metaphor, while intuitive, is not a perfect fit. It is overly suggestive of a human actor who has studied a character in advance — their personality, history, likes and dislikes, and so on — and proceeds to play that character in the ensuing dialogue. But a dialogue agent based on an LLM does not commit to playing a single, well defined role in advance. Rather, it generates a distribution of characters, and refines that distribution as the dialogue progresses. The dialogue agent is more like a performer in improvisational theatre than an actor in a conventional, scripted play.

To better reflect this distributional property, we can think of an LLM as a non-deterministic simulator capable of role-playing an infinity of characters, or, to put it another way, capable of stochastically generating an infinity of simulacra (Janus, 2022). According to this framing, the dialogue agent doesn’t realise a single simulacrum, a single character. Rather, as the conversation proceeds, the dialogue agent maintains a superposition of simulacra that are consistent with the preceding context, where a superposition is a distribution over all possible simulacra.

Consider that, at each point during the ongoing production of a sequence of tokens, theLLM outputs a distribution over possible next tokens. Each such token represents a possible continuation of the sequence, and each of these continuations could itself be continued in a multitude of ways. In other words, from the most recently generated token, a tree of possibilities branches out (Fig. 3). This tree can be thought of as a multiverse, where each branch represents a distinct narrative path, or a distinct “world” (Reynolds and McDonell, 2021).

At each node, the set of possible next tokens exists in superposition, and to sample a token is to collapse this superposition to a single token. Autoregressively sampling the model picks out a single, linear path through the tree. But there is no obligation to follow a linear path. With the aid of a suitably designed interface, a user can explore multiple branches, keeping track of nodes where a narrative diverges in interesting ways, revisiting alternative branches at leisure.”