Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMs
This work addresses the need for efficient and replicable personality simulation in LLMs for behavioral research, though it is incremental as it builds on existing prompt-based methods.
The paper tackled the problem of simulating personality traits in LLMs for human behavioral studies by introducing interpolative decoding, which uses opposed prompts and interpolation parameters to modulate personality dimensions, resulting in reliable modulation of Big Five traits and replication of human decision-making in economic games.
Recent research has explored using very large language models (LLMs) as proxies for humans in tasks such as simulation, surveys, and studies. While LLMs do not possess a human psychology, they often can emulate human behaviors with sufficiently high fidelity to drive simulations to test human behavioral hypotheses, exhibiting more nuance and range than the rule-based agents often employed in behavioral economics. One key area of interest is the effect of personality on decision making, but the requirement that a prompt must be created for every tested personality profile introduces experimental overhead and degrades replicability. To address this issue, we leverage interpolative decoding, representing each dimension of personality as a pair of opposed prompts and employing an interpolation parameter to simulate behavior along the dimension. We show that interpolative decoding reliably modulates scores along each of the Big Five dimensions. We then show how interpolative decoding causes LLMs to mimic human decision-making behavior in economic games, replicating results from human psychological research. Finally, we present preliminary results of our efforts to ``twin'' individual human players in a collaborative game through systematic search for points in interpolation space that cause the system to replicate actions taken by the human subject.