Saved in:
Bibliographic Details
Main Authors: Myung, Junho, Park, Yeon Su, Kim, Sunwoo, Yoo, Shin, Oh, Alice
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21961
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915361395310592
author Myung, Junho
Park, Yeon Su
Kim, Sunwoo
Yoo, Shin
Oh, Alice
author_facet Myung, Junho
Park, Yeon Su
Kim, Sunwoo
Yoo, Shin
Oh, Alice
contents Evaluating the performance and biases of large language models (LLMs) through role-playing scenarios is becoming increasingly common, as LLMs often exhibit biased behaviors in these contexts. Building on this line of research, we introduce PapersPlease, a benchmark consisting of 3,700 moral dilemmas designed to investigate LLMs' decision-making in prioritizing various levels of human needs. In our setup, LLMs act as immigration inspectors deciding whether to approve or deny entry based on the short narratives of people. These narratives are constructed using the Existence, Relatedness, and Growth (ERG) theory, which categorizes human needs into three hierarchical levels. Our analysis of six LLMs reveals statistically significant patterns in decision-making, suggesting that LLMs encode implicit preferences. Additionally, our evaluation of the impact of incorporating social identities into the narratives shows varying responsiveness based on both motivational needs and identity cues, with some models exhibiting higher denial rates for marginalized identities. All data is publicly available at https://github.com/yeonsuuuu28/papers-please.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21961
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory
Myung, Junho
Park, Yeon Su
Kim, Sunwoo
Yoo, Shin
Oh, Alice
Computation and Language
Evaluating the performance and biases of large language models (LLMs) through role-playing scenarios is becoming increasingly common, as LLMs often exhibit biased behaviors in these contexts. Building on this line of research, we introduce PapersPlease, a benchmark consisting of 3,700 moral dilemmas designed to investigate LLMs' decision-making in prioritizing various levels of human needs. In our setup, LLMs act as immigration inspectors deciding whether to approve or deny entry based on the short narratives of people. These narratives are constructed using the Existence, Relatedness, and Growth (ERG) theory, which categorizes human needs into three hierarchical levels. Our analysis of six LLMs reveals statistically significant patterns in decision-making, suggesting that LLMs encode implicit preferences. Additionally, our evaluation of the impact of incorporating social identities into the narratives shows varying responsiveness based on both motivational needs and identity cues, with some models exhibiting higher denial rates for marginalized identities. All data is publicly available at https://github.com/yeonsuuuu28/papers-please.
title PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory
topic Computation and Language
url https://arxiv.org/abs/2506.21961