Improving Behavioral Alignment in LLM Social Simulations via Context Formation and Navigation

TL;DR

This paper introduces a two-stage framework involving context formation and navigation to improve how well large language models mimic human decision-making in complex social simulations, validated across multiple environments and models.

Contribution

It proposes a novel two-stage approach for aligning LLM behavior with humans in social decision tasks, emphasizing the importance of explicit context setup and guided reasoning.

Findings

Both stages are necessary for complex environments to match human behavior.

Simpler tasks only require context formation for alignment.

The framework enhances the systematic design of LLM social simulations.

Abstract

Large language models (LLMs) are increasingly used to simulate human behavior in experimental settings, but they systematically diverge from human decisions in complex decision-making environments, where participants must anticipate others' actions and form beliefs based on observed behavior. We propose a two-stage framework for improving behavioral alignment. The first stage, context formation, explicitly specifies the experimental design to establish an accurate representation of the decision task and its context. The second stage, context navigation, guides the reasoning process within that representation to make decisions. We validate this framework through a focal replication of a sequential purchasing game with quality signaling (Kremer and Debo, 2016), extending to a crowdfunding game with costly signaling (Cason et al., 2025) and a demand-estimation task (Gui and Toubia, 2025) to test generalizability across decision environments. Across four state-of-the-art (SOTA) models (GPT-4o, GPT-5, Claude-4.0-Sonnet-Thinking, DeepSeek-R1), we find that complex decision-making environments require both stages to achieve behavioral alignment with human benchmarks, whereas the simpler demand-estimation task requires only context formation. Our findings clarify when each stage is necessary and provide a systematic approach for designing and diagnosing LLM social simulations as complements to human subjects in behavioral research.