Conditioning LLMs on Social Value Orientation improves behavioural alignment in a sequential social dilemma

2026-10-01

AI Summary

This study addresses the insufficient behavioral heterogeneity exhibited by large language models (LLMs) when simulating human decision-making, which results in significant deviations from empirical distributions. To mitigate this, we propose a conditional prompting framework grounded in Social Value Orientation (SVO) to align LLM behavior within sequential social dilemmas. Our research reveals that LLMs do not require stable intrinsic preferences; rather, mapping social preferences onto strategic choices suffices to enhance simulation validity. We implement SVO-conditioned interventions on eight LLMs using experimental data from Centipede games. The proposed approach improves behavioral alignment by up to 70% relative to default prompting conditions and successfully replicates the established association between prosociality and cooperation. These findings offer a novel paradigm for simulating social behavior with LLMs.

Abstract

Large language Models (LLMs) are increasingly used to simulate human decision-making, yet their outputs often under-represent human behavioural heterogeneity. We investigate whether conditioning LLMs on Social Value Orientation (SVO, a measure of how individuals value their own outcomes relative to others') can better reproduce human behaviour in a sequential social dilemma. Using experimental data from two variants of the Centipede Game (CG) as reference, we compare the default behaviour of eight LLMs with behaviour generated after conditioning them on SVO profiles drawn from the human sample. We find that the default strategies vary substantially across models, but are generally distant from the reference distributions. However, conditioning them on SVO profiles systematically steers their strategic behaviour, improving alignment with the human reference by up to 70% with respect to the default. Across models, higher induced SVO values decrease the probability of stopping the game, reproducing the relationship between prosociality and cooperation observed in human behaviour. Together with the sensitivity of LLMs' elicited SVO to prompt and order effects, these results suggest that the usefulness of SVO for behavioural simulation does not depend on LLMs possessing stable social preferences, but rather on their ability to map social preferences onto corresponding strategic choices.

Problem

• Large Language Models
• Social Value Orientation
• Behavioural Alignment
• Sequential Social Dilemma
• Centipede Game

Innovation

• Social Value Orientation
• Large Language Models
• Sequential Social Dilemma
• Behavioral Alignment
• Centipede Game