Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hosseini, Hadi, Khanna, Samarth
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911279192473600
author Hosseini, Hadi
Khanna, Samarth
author_facet Hosseini, Hadi
Khanna, Samarth
contents The growing interest in employing large language models (LLMs) for decision-making in social and economic contexts has raised questions about their potential to function as agents in these domains. A significant number of societal problems involve the distribution of resources, where fairness, along with economic efficiency, play a critical role in the desirability of outcomes. In this paper, we examine whether LLM responses adhere to fundamental fairness concepts such as equitability, envy-freeness, and Rawlsian maximin, and investigate their alignment with human preferences. We evaluate the performance of several LLMs, providing a comparative benchmark of their ability to reflect these measures. Our results demonstrate a lack of alignment between current LLM responses and human distributional preferences. Moreover, LLMs are unable to utilize money as a transferable resource to mitigate inequality. Nonetheless, we demonstrate a stark contrast when (some) LLMs are tasked with selecting from a predefined menu of options rather than generating one. In addition, we analyze the robustness of LLM responses to variations in semantic factors (e.g., intentions or personas) or non-semantic prompting changes (e.g., templates or orderings). Finally, we highlight potential strategies aimed at enhancing the alignment of LLM behavior with well-established fairness concepts.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
Hosseini, Hadi
Khanna, Samarth
Computer Science and Game Theory
Artificial Intelligence
Computation and Language
Multiagent Systems
The growing interest in employing large language models (LLMs) for decision-making in social and economic contexts has raised questions about their potential to function as agents in these domains. A significant number of societal problems involve the distribution of resources, where fairness, along with economic efficiency, play a critical role in the desirability of outcomes. In this paper, we examine whether LLM responses adhere to fundamental fairness concepts such as equitability, envy-freeness, and Rawlsian maximin, and investigate their alignment with human preferences. We evaluate the performance of several LLMs, providing a comparative benchmark of their ability to reflect these measures. Our results demonstrate a lack of alignment between current LLM responses and human distributional preferences. Moreover, LLMs are unable to utilize money as a transferable resource to mitigate inequality. Nonetheless, we demonstrate a stark contrast when (some) LLMs are tasked with selecting from a predefined menu of options rather than generating one. In addition, we analyze the robustness of LLM responses to variations in semantic factors (e.g., intentions or personas) or non-semantic prompting changes (e.g., templates or orderings). Finally, we highlight potential strategies aimed at enhancing the alignment of LLM behavior with well-established fairness concepts.
title Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
topic Computer Science and Game Theory
Artificial Intelligence
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2502.00313