Work

Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation

Year: 2025

Type: conference-paper

Abstract: Morality serves as the foundation of societal structure, guiding legal systems, shaping cultural values, and influencing individual selfperception.With the rise and pervasiveness of generative AI tools, and particularly Large Language Models (LLMs), concerns arise regarding how these tools capture and potentially alter moral dimensions through machine-generated text manipulation.Based on the Moral Foundation Theory, our work investigates this topic by analyzing the behavior of 12 LLMs among the most widely used Open and uncensored (i.e., "abliterated") models, and leveraging humanannotated datasets used in moral-related analysis.Results have shown varying levels of alteration of moral expressions depending on the type of text modification task and moral-related conditioning prompt.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2025.acl-long.883

Authors: Candida Maria Greco, Lucio La Cava, Lorenzo Zangari, Andrea Tagarelli

Institution: University of Calabria

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: NextGenerationEU

Awards: G231133531, G3822624842