Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.18469 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917352700903424 |
|---|---|
| author | Kawarada, Masayuki Watanabe, Kodai Murakami, Soichiro |
| author_facet | Kawarada, Masayuki Watanabe, Kodai Murakami, Soichiro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18469 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms Kawarada, Masayuki Watanabe, Kodai Murakami, Soichiro Computation and Language 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. |
| title | GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.18469 |