Image de couverture de livre

The Morality of Probability: How Implicit Moral Biases in LLMs May Shape the Future of Human-AI Symbiosis

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	O'Doherty, Eoin, Weinrauch, Nicole, Talone, Andrew, Klempner, Uri, Yi, Xiaoyuan, Xie, Xing, Zeng, Yi
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MoVa: Towards Generalizable Classification of Human Morals and Values
par: Chen, Ziyu, et autres
Publié: (2025)

Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs
par: Ma, Huanhuan, et autres
Publié: (2025)

Morally Programmed LLMs Reshape Human Morality
par: Lyu, Pengzhao, et autres
Publié: (2026)

Write on Paper, Wrong in Practice: Why LLMs Still Struggle with Writing Clinical Notes
par: Kupferschmidt, Kristina L., et autres
Publié: (2025)

Implicit Humanization in Everyday LLM Moral Judgments
par: Ayad, Hoda, et autres
Publié: (2026)

Inducing Human-like Biases in Moral Reasoning Language Models
par: Karpov, Artem, et autres
Publié: (2024)

Influenza Vaccine Effectiveness During the 2023/2024 Season: A Test‐Negative Case–Control Study Among Emergency Hospital Admissions With Respiratory Conditions in Northern Ireland
par: Magda Bucholc, et autres
Publié: (2025)

MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?
par: Yong, Xixian, et autres
Publié: (2025)

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
par: Zhang, Xiangxu, et autres
Publié: (2026)

Future Morality
Publié: (2022)

MoralBench: Moral Evaluation of LLMs
par: Ji, Jianchao, et autres
Publié: (2024)

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
par: Zhang, Zhaowei, et autres
Publié: (2026)

Data-Efficient Domain Adaptation for LLM-based MT using Contrastive Preference Optimization
par: Vieira, Inacio, et autres
Publié: (2025)

From Morality Installation in LLMs to LLMs in Morality-as-a-System
par: Bombaerts, Gunter
Publié: (2026)

Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment
par: Vida, Karina, et autres
Publié: (2024)

Moral Judgments in Online Discourse are not Biased by Gender
par: Betti, Lorenzo, et autres
Publié: (2024)

How do Role Models Shape Collective Morality? Exemplar-Driven Moral Learning in Multi-Agent Simulation
par: Liao, Junjie, et autres
Publié: (2026)

CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
par: Yao, Jing, et autres
Publié: (2024)

O “Bem Básico” como princípio substantivo da ação desconfiada: a economia de tensão em viagens de ônibus no Rio de Janeiro
par: Vittorio Talone
Publié: (2017)

Evitação e afastamento como dispositivos morais da gramática da desconfiança: Uma leitura pragmatista do deslocamento urbano pela 'violenta' cidade do Rio de Janeiro
par: Vittorio Talone
Publié: (2018)

Variations of the Self: The Continuity of Life after Contact with Violent Death
par: Vittorio Talone
Publié: (2023)

Exploring a De Novo Route to Bradyrhizose: Synthesis and Isomeric Equilibrium of Bradyrhizose Diastereomers≠
par: Vitor L. S. Cunha, et autres
Publié: (2024)

Audiovisual Materials in Support of Information Science Curricula: An Annotated Listing with Subject Index. Second Edition, Revised and Expanded.
par: Klempner, Irving M.
Publié: (1977)

Audiovisual Materials in Support of Information Science Curricula: An Annotated Listing with Subject Index. First Edition, Revised.
par: Klempner, Irving M.
Publié: (1972)

Audiovisual Materials in Support of Information Science Curricula: An Annotated Listing with Subject Index.
par: Klempner, Irving M.
Publié: (1971)

Decisions for Library School Curricula
par: Klempner, Irving M.
Publié: (1976)

The Incomplete Bridge: How AI Research (Mis)Engages with Psychology
par: Jiang, Han, et autres
Publié: (2025)

Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches
par: Biedma, Pablo, et autres
Publié: (2024)

Smart But Not Moral? Moral Alignment In Human-AI Decision-Making
par: Ernst, Christiane, et autres
Publié: (2026)

Moral Mazes in the Era of LLMs
par: Nguyen, Dang, et autres
Publié: (2026)

The Straight and Narrow: Do LLMs Possess an Internal Moral Path?
par: Hu, Luoming, et autres
Publié: (2026)

Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning
par: Oliveira, Nigini, et autres
Publié: (2023)

How Responses to Sexual Harassment and Moral Values Shape Investment Decision Making
par: Amal P. Abeysekera, et autres
Publié: (2026)

How to Reduce Time Theft Behavior in Telework: A Moral Self‐Regulation Perspective
par: Bingqian Liang, et autres
Publié: (2025)

Moral Choices for Our Future Selves
par: Viganò, Eleonora
Publié: (2022)

Conference on Education for Information Science--Strategies for Change in Library School Programs.
par: Klempner, Irving M., Ed.
Publié: (1978)

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs
par: Thomas, Rohan Subramanian, et autres
Publié: (2026)

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
par: Yuan, Chenchen, et autres
Publié: (2026)

How LLMs are Shaping the Future of Virtual Reality
par: Özkaya, Süeda, et autres
Publié: (2025)

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
par: Jiang, Han, et autres
Publié: (2025)