The Value of Gen-AI Conversations: A bottom-up Framework for AI Value Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Motnikar, Lenart, Baum, Katharina, Kagan, Alexander, Spiekermann-Hoff, Sarah
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918106517995520
author Motnikar, Lenart
Baum, Katharina
Kagan, Alexander
Spiekermann-Hoff, Sarah
author_facet Motnikar, Lenart
Baum, Katharina
Kagan, Alexander
Spiekermann-Hoff, Sarah
contents Conversational agents (CAs) based on generative artificial intelligence frequently face challenges ensuring ethical interactions that align with human values. Current value alignment efforts largely rely on top-down approaches, such as technical guidelines or legal value principles. However, these methods tend to be disconnected from the specific contexts in which CAs operate, potentially leading to misalignment with users interests. To address this challenge, we propose a novel, bottom-up approach to value alignment, utilizing the value ontology of the ISO Value-Based Engineering standard for ethical IT design. We analyse 593 ethically sensitive system outputs identified from 16,908 conversational logs of a major European employment service CA to identify core values and instances of value misalignment within real-world interactions. The results revealed nine core values and 32 different value misalignments that negatively impacted users. Our findings provide actionable insights for CA providers seeking to address ethical challenges and achieve more context-sensitive value alignment.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21091
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Value of Gen-AI Conversations: A bottom-up Framework for AI Value Alignment
Motnikar, Lenart
Baum, Katharina
Kagan, Alexander
Spiekermann-Hoff, Sarah
Computers and Society
Artificial Intelligence
Conversational agents (CAs) based on generative artificial intelligence frequently face challenges ensuring ethical interactions that align with human values. Current value alignment efforts largely rely on top-down approaches, such as technical guidelines or legal value principles. However, these methods tend to be disconnected from the specific contexts in which CAs operate, potentially leading to misalignment with users interests. To address this challenge, we propose a novel, bottom-up approach to value alignment, utilizing the value ontology of the ISO Value-Based Engineering standard for ethical IT design. We analyse 593 ethically sensitive system outputs identified from 16,908 conversational logs of a major European employment service CA to identify core values and instances of value misalignment within real-world interactions. The results revealed nine core values and 32 different value misalignments that negatively impacted users. Our findings provide actionable insights for CA providers seeking to address ethical challenges and achieve more context-sensitive value alignment.
title The Value of Gen-AI Conversations: A bottom-up Framework for AI Value Alignment
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2507.21091