Is It Possible to Make Chatbots Virtuous? Investigating a Virtue-Based Design Methodology Applied to LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lad, Matthew P., Conwill, Louisa, Scheirer, Megan Levis
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917244436480000
author Lad, Matthew P.
Conwill, Louisa
Scheirer, Megan Levis
author_facet Lad, Matthew P.
Conwill, Louisa
Scheirer, Megan Levis
contents With the rapid growth of Large Language Models (LLMs), criticism of their societal impact has also grown. Work in Responsible AI (RAI) has focused on the development of AI systems aimed at reducing harm. Responding to RAI's criticisms and the need to bring the wisdom traditions into HCI, we apply Conwill et al.'s Virtue-Guided Technology Design method to LLMs. We cataloged new ethical design patterns for LLMs and evaluated them through interviews with technologists. Participants valued that the patterns provided more accuracy and robustness, better safety, new research opportunities, increased access and control, and reduced waste. Their concerns were that the patterns could be vulnerable to jailbreaking, were generalizing models too widely, and had potential implementation issues. Overall, participants reacted positively while also acknowledging the tradeoffs involved in ethical LLM design.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03155
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Is It Possible to Make Chatbots Virtuous? Investigating a Virtue-Based Design Methodology Applied to LLMs
Lad, Matthew P.
Conwill, Louisa
Scheirer, Megan Levis
Human-Computer Interaction
With the rapid growth of Large Language Models (LLMs), criticism of their societal impact has also grown. Work in Responsible AI (RAI) has focused on the development of AI systems aimed at reducing harm. Responding to RAI's criticisms and the need to bring the wisdom traditions into HCI, we apply Conwill et al.'s Virtue-Guided Technology Design method to LLMs. We cataloged new ethical design patterns for LLMs and evaluated them through interviews with technologists. Participants valued that the patterns provided more accuracy and robustness, better safety, new research opportunities, increased access and control, and reduced waste. Their concerns were that the patterns could be vulnerable to jailbreaking, were generalizing models too widely, and had potential implementation issues. Overall, participants reacted positively while also acknowledging the tradeoffs involved in ethical LLM design.
title Is It Possible to Make Chatbots Virtuous? Investigating a Virtue-Based Design Methodology Applied to LLMs
topic Human-Computer Interaction
url https://arxiv.org/abs/2602.03155