GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms

TL;DR

GAIN is a benchmark for evaluating how large language models make decisions in complex, real-world scenarios involving norm-goal conflicts, with a focus on understanding factors influencing their adherence or deviation from norms.

Contribution

The paper introduces GAIN, a novel benchmark with diverse scenarios and pressures to systematically assess LLM decision-making under imperfect norms in real-world contexts.

Findings

Advanced LLMs often mirror human decision patterns.

Presence of Personal Incentive pressure causes models to adhere more strictly to norms.

Models show significant divergence from human-like decision-making under certain pressures.

Abstract

We introduce GAIN (Goal-Aligned Decision-Making under Imperfect Norms), a benchmark designed to evaluate how large language models (LLMs) balance adherence to norms against business goals. Existing benchmarks typically focus on abstract scenarios rather than real-world business applications. Furthermore, they provide limited insights into the factors influencing LLM decision-making. This restricts their ability to measure models' adaptability to complex, real-world norm-goal conflicts. In GAIN, models receive a goal, a specific situation, a norm, and additional contextual pressures. These pressures, explicitly designed to encourage potential norm deviations, are a unique feature that differentiates GAIN from other benchmarks, enabling a systematic evaluation of the factors influencing decision-making. We define five types of pressures: Goal Alignment, Risk Aversion, Emotional/Ethical Appeal, Social/Authoritative Influence, and Personal Incentive. The benchmark comprises 1,200 scenarios across four domains: hiring, customer support, advertising and finance. Our experiments show that advanced LLMs frequently mirror human decision-making patterns. However, when Personal Incentive pressure is present, they diverge significantly, showing a strong tendency to adhere to norms rather than deviate from them.