Diverse Human Value Alignment for Large Language Models via Ethical Reasoning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Jiahao, Xue, Songkai, Li, Jinghui, Wang, Xiaozhen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915591611219968
author Wang, Jiahao
Xue, Songkai
Li, Jinghui
Wang, Xiaozhen
author_facet Wang, Jiahao
Xue, Songkai
Li, Jinghui
Wang, Xiaozhen
contents Ensuring that Large Language Models (LLMs) align with the diverse and evolving human values across different regions and cultures remains a critical challenge in AI ethics. Current alignment approaches often yield superficial conformity rather than genuine ethical understanding, failing to address the complex, context-dependent nature of human values. In this paper, we propose a novel ethical reasoning paradigm for LLMs inspired by well-established ethical decision-making models, aiming at enhancing diverse human value alignment through deliberative ethical reasoning. Our framework consists of a structured five-step process, including contextual fact gathering, hierarchical social norm identification, option generation, multiple-lens ethical impact analysis, and reflection. This theory-grounded approach guides LLMs through an interpretable reasoning process that enhances their ability to understand regional specificities and perform nuanced ethical analysis, which can be implemented with either prompt engineering or supervised fine-tuning methods. We perform evaluations on the SafeWorld benchmark that specially designed for regional value alignment. Experimental results demonstrate our framework significantly improves LLM alignment with diverse human values compared to baseline methods, enabling more accurate social norm identification and more culturally appropriate reasoning. Our work provides a concrete pathway toward developing LLMs that align more effectively with the multifaceted values of global societies through interdisciplinary research.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00379
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
Wang, Jiahao
Xue, Songkai
Li, Jinghui
Wang, Xiaozhen
Artificial Intelligence
Computation and Language
Ensuring that Large Language Models (LLMs) align with the diverse and evolving human values across different regions and cultures remains a critical challenge in AI ethics. Current alignment approaches often yield superficial conformity rather than genuine ethical understanding, failing to address the complex, context-dependent nature of human values. In this paper, we propose a novel ethical reasoning paradigm for LLMs inspired by well-established ethical decision-making models, aiming at enhancing diverse human value alignment through deliberative ethical reasoning. Our framework consists of a structured five-step process, including contextual fact gathering, hierarchical social norm identification, option generation, multiple-lens ethical impact analysis, and reflection. This theory-grounded approach guides LLMs through an interpretable reasoning process that enhances their ability to understand regional specificities and perform nuanced ethical analysis, which can be implemented with either prompt engineering or supervised fine-tuning methods. We perform evaluations on the SafeWorld benchmark that specially designed for regional value alignment. Experimental results demonstrate our framework significantly improves LLM alignment with diverse human values compared to baseline methods, enabling more accurate social norm identification and more culturally appropriate reasoning. Our work provides a concrete pathway toward developing LLMs that align more effectively with the multifaceted values of global societies through interdisciplinary research.
title Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2511.00379