Skip to content

Similar papers

Conference Open access Oct 2026

The Artificial Moral Machine: Do LLMs Mirror Human Moral Diversity or Merely Caricature It?

Persona conditioning is the practice of prompting LLMs to adopt specific demographic identities. Although it is increasingly used to simulate human perspectives, its fidelity in the moral domain is untested at scale. We address this gap by testing moral fidelity on three LLMs of different sizes: gpt-4.1-nano (the small...

Davide Liga, Liu-Wen Yu, M. Slavkovik et al. · 0 citations
#natural language process... Preprint Oct 2026

Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs

Large language models are increasingly deployed in morally and legally sensitive contexts, yet little is known about how they internally represent distinctions between moral reasoning styles. We ask whether a model's differential response to rule-framed and consequence-framed moral questions reflects distinct internal...

Eugenie Shi · 1 citation
#natural language process... Preprint Oct 2026

Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs

Social psychology has long described how people can be persuaded to interpret a harmful act as moral. Recent research suggests that Large Language Models (LLMs) echo aspects of human psychology, from cognitive biases to social conformity. This raises a question with direct safety implications: can LLMs be moralized to...

Adel Khorramrouz, Yi-Chia Wang, Sharon Levy · 0 citations
#large language models Open access Aug 2026

Can Analytic Theology Provide a Symbolic Logical Framework for Moral Safeguards in Large Language Models?

Whether analytic theology can supply a symbolic logical framework apt to encode moral safeguards inside LLM pipelines is investigated, which targets the engineering of moral computation: a formal language placed between metaphysical content and machine implementation.

Fernando Negrini · 0 citations
#small language model Open access Sep 2026

Measuring structural value alignment in sixteen models: LLMs have human-like moral spaces

Evaluating whether large language models (LLMs) reason about morality in human-like ways requires more than measuring whether they produce the right outputs in isolated cases. Existing approaches – including scalar agreement, distributional analysis, rationale classification, and consistency testing – compare model and...

Ye-Xiang Tang · 0 citations
Oct 2026

Worldview sovereignty and sovereign morality in LLMs: a cross-lingual experiment

All six models – regardless of their country of origin or interface language – reproduce the Western civilisational profile as the dominant response strategy across the tested models, providing empirical evidence for the dominance of a Western value profile across the tested models.

E. Tikhomirova, Dushkin Roman Viktorovich, Kuzmin Aleksey Alekseevich et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.