Framing the Game: How Context Shapes LLM Decision-Making
This work addresses the need for dynamic, context-aware evaluation methodologies for LLM deployments in real-world applications, though it is incremental in focusing on framing effects within existing evaluation paradigms.
The study tackled the problem of how context framing affects LLM decision-making by introducing a novel evaluation framework that systematically varies scenarios, revealing significant and predictable contextual variability in responses.
Large Language Models (LLMs) are increasingly deployed across diverse contexts to support decision-making. While existing evaluations effectively probe latent model capabilities, they often overlook the impact of context framing on perceived rational decision-making. In this study, we introduce a novel evaluation framework that systematically varies evaluation instances across key features and procedurally generates vignettes to create highly varied scenarios. By analyzing decision-making patterns across different contexts with the same underlying game structure, we uncover significant contextual variability in LLM responses. Our findings demonstrate that this variability is largely predictable yet highly sensitive to framing effects. Our results underscore the need for dynamic, context-aware evaluation methodologies for real-world deployments.