Psychology of Moral and Emotional Judgment

Latest papers

• Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigations

  Ismael T. Freire, Marceau Nahon, Maud van Lier, Katie Evans, H\'elie Bazin, Michele Farisco, Kathinka Evers, Raja Chatila, Mehdi Khamassi · 1 October 2026

  Large Language Models (LLMs) and more broadly Artificial Intelligence (AI) systems are often described and understood in human-like terms, a phenomenon known as \emph{anthropomorphism}. This paper provides a synthesis of recent literature on anthropomorphism in AI, covering theoretical frameworks, t…

• One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning

  Sualeha Farid, Jayden Lin, Zean Chen, Shivani Kumar, David Jurgens · 30 September 2026

  Large Language Models (LLMs) are increasingly deployed across multilingual and multicultural settings, yet it remains unclear whether changing language leads models to adopt community-specific moral reasoning or merely changes how shared learned abstractions are expressed. We conduct a controlled mu…

• Echoes of Deeds: Moral History Can Shape and Steer LLM Behavioral Choices

  Lucio La Cava, Andrea Tagarelli · 29 September 2026

  Evaluations of Large Language Models (LLMs) morality typically consider decisions in isolation, thus overlooking whether an individual's unrelated prior conduct influences the model's subsequent choices. This leaves open the question of whether, and to what extent, moral history shapes LLM decisiona…

• Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models

  Utkarsh Agarwal, Monojit Choudhury · 21 September 2026

  Large Language Models (LLMs) are increasingly deployed in applications that must weigh clashing moral values, yet even strong models exhibit hidden biases and brittle instruction-following across languages. We introduce a 12,000-instance dataset of two-option dilemmas covering pairwise three value c…

• Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30

  Hans Andersen, David Dichas · 21 September 2026

  Recent work applies human psychometric questionnaires to large language models to elicit moral and value profiles, but it is not clear whether these instruments measure anything stable in models or whether the resulting profiles can be moved toward a target human population. We administer the Norweg…

• Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions Across Model Families

  Orion Reblitz-Richardson · 15 September 2026

  Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model stops refusing harmful requests. That fact says how easily refusal can be removed, not what the refusal decision was reading in the first place. We ask…

• Moral Rebel Agents: Decision-Making Under Conflicting Obligations

  Hector Munoz-Avila, David W. Aha, Paola Rizzo · 15 September 2026

  Autonomous agents are typically obliged to follow user-assigned tasks. However, strict obedience may conflict with moral obligations that arise during execution. This paper investigates \textbf{moral rebellion}: the ability of an autonomous agent to deviate from a user-assigned task when morally jus…

• AI Use Conditions and Perspective Diversity in Ethical Decision-Making: A Pilot Study of Human Reasoning Processes

  Byeongmu Choi · 15 September 2026

  Generative artificial intelligence (AI) is increasingly used to support human decision-making, yet less attention has been paid to how AI may influence the reasoning processes that precede final judgments. This pilot study explored whether different AI-use conditions were associated with differences…

• Steering Geometry: Validating Human Value Geometry in LLM Steering Space

  Mohammad Mahdi Abootorabi, Armin Saghafian, Ali Bazshoushtari, Hamid Rezaei, EunJeong Hwang, Vered Shwartz, Parvin Mousavi, Purang Abolmaesumi · 9 September 2026

  As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inference-time alternative to fine-tuning methods (e.g., RLHF, DPO) for behavioral control. However, existing work typically validates steering on isolated beh…

• Human-like moral judgments conceal divergent motive attributions in large language models

  Xiaoyan Wu, Jean-Claude Dreher · 9 September 2026

  Large language models (LLMs) are used to simulate human participants in psychological research. We asked whether LLMs that reproduce human evaluations of a whistleblower's moral character also reproduce the motive attributions that accompany them. Five LLMs and two human samples (N = 125 and N = 742…

• Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models

  Sunny Rai, Jinyi Kuang, Reyhan Jamalova, Annie Lou, Cristina Bicchieri, Niyati Malhotra, Victor Hugo Orozco-Olvera, Ana Maria Munoz-Boudet, Lyle H Ungar, Sharath C Guntuku · 9 September 2026

  Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `do not steal'). However, social intelligence depends not only on norm recognition, but also on anticipating who will enforce it and how (e.g., publi…

• How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions

  Fernanda Mansilla, Aloysius Tok, Bahia Guella\"i, Farah Benamara, Nancy F. Chen · 7 September 2026

  As LLMs take on roles requiring moral advice, understanding how they attribute moral agency becomes critical. Humans possess moral agency, the capacity to make ethically guided decisions and bear responsibility for their consequences, a well-established construct in moral psychology. Yet as artifici…

• Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?

  Daan R. Henselmans, Derck W. E. Prinzhorn, Arno Libert · 7 September 2026

  AI oversight methods rely on ground truth for validation, but what constitutes appropriate AI behavior is contested. This leaves evaluation of moral reasoning in LLMs and debate-based oversight implicitly avoiding realistic ambiguity. We investigate an alternative standard designed to function despi…

• Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment

  Arno Libert, Derck W. E. Prinzhorn, Daan R. Henselmans · 7 September 2026

  AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value pluralism there is no correct target, but a shared prerequisite is that the system's behavior expresses a coherent policy: a mapping from situations to verdicts that is invariant while a situation's morally…

• Moral Advice as Interactional Negotiation: Framing, User Pressure, and Social Position in Large Language Model Responses

  Minne Chen, Yourong Yao · 7 September 2026

  As conversational AI becomes a source of everyday guidance, LLMs increasingly participate in the interpretation and legitimation of morally contested choices. We examine LLM moral advice as an interactional negotiation shaped by framing, sustained user pressure, and the moral subject's social positi…

• Controversy and Group Certainty Jointly Shape Everyday Moral Judgments

  Ziyu Chen, Minjeong Shin, Tuan Dung Nguyen, Colin Klein, Chenhao Tan, Nick Schuster, Nicholas George Carroll, Alasdair Tran, Lexing Xie · 7 September 2026

  Everyday moral life rarely resembles a trolley problem. It involves disputes about families, relationships, work, money, and care, situations in which people often encounter the judgments of others. We examined how judgments about nuanced interpersonal dilemmas respond to social information that con…

• Representational alignment yields generalizable safety in language models

  Lingyu Li, Yan Teng, Yingchun Wang, Xia Hu · 4 September 2026

  Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet models remain vulnerable when the same harmful intent is recast in unfamiliar or adversarial forms that humans can easily recognize. Prototype theory offe…

• Caught in the Story: Narrative Captivity in Multi-turn LLMs Conversation

  Yuhe Wu, Guangyu Wang, Yujie Chen, Jiatong Zhang, Yuran Chen, Yutong Zhang, Xiyin Cheng, Wenpeng Cao, Zhuang Liu, Guang Zhang · 4 September 2026

  People increasingly turn to large language models (LLMs) for everyday advice, making ethically charged interpersonal problems a practical moral-advisory context. Most prior work has studied this context through single-turn judgments or pressure-laden rebuttals, assumptions that poorly match how guid…

• Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI

  Shang Lu · 3 September 2026

  With the development of artificial intelligence (AI), the landscape of meta-ethics, which has largely centred on human ethics, faces pressures that may significantly reconfigure it. In particular, if future AI systems were to exhibit sufficiently integrated capacities for moral reasoning, moral inte…

• How Language Models Organize and Structure Moral Knowledge

  Orion Reblitz-Richardson · 28 August 2026

  How do large language models (LLMs) organize moral knowledge? Models detect moral content broadly, but detection is a low bar. We ask whether they go further, distinguishing moral foundations from one another and organizing the relationships between them geometrically. We train six independent lin…

• Incoherent by Design? On the Moral Self-Consistency of LLMs

  Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana, Helen Nissenbaum · 18 August 2026

  LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed. This inconsistency is a problem for any sys…

• Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture

  Aidan Kierans, Ritam Dutt, Kaley Rittichier, Shiri Dori-Hacohen, Avijit Ghosh · 18 August 2026

  Recent work on evaluating the moral competence of large language models (LLMs) has focused primarily on what we call the moral value problem, i.e., whether model outputs align with human moral values. In contrast, the moral norm problem, i.e., whether models can identify and correctly apply context-…

• Participatory Moral AI Is Not Neutral: The Invisible Hand of Developers

  Taenyun Kim, Edyta Bogucka, Daniele Quercia · 17 August 2026

  As AI systems make more morally loaded decisions across society, one response has been moral preference elicitation. In this approach, researchers poll participants on hypothetical dilemmas and use the aggregated votes to train a policy that an AI model then applies at scale. Before any vote is cast…

• Falsehood and Impossibility Are Different Directions in an AI's Representation of Language

  Yoon Pyo Lee · 14 August 2026

  Language can describe states of affairs that are false and states of affairs that could not be the case at all. Whether an AI model internally distinguishes these failures remains unclear. I report an exploratory activation study of the multimodal open-weight model Gemma 3 4B IT using 85 prompts fro…

• Metanormative Theory for RL-Based Moral Agents

  Aleks Knoks, Marija Slavkovik · 11 August 2026

  The overlapping disciplines of machine ethics and value alignment are concerned with designing artificial agents that are aligned with human values and that act in ethically acceptable ways. A recent trend in these disciplines is the use of reinforcement learning (RL) to design such agents, sidelini…