Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Farid, Sualeha, Lin, Jayden, Chen, Zean, Kumar, Shivani, Jurgens, David
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoral
di: Kumar, Shivani, et al.
Pubblicazione: (2025)

The Fellowship of the LLMs: Multi-Model Workflows for Synthetic Preference Optimization Dataset Generation
di: Arif, Samee, et al.
Pubblicazione: (2024)

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs
di: Thomas, Rohan Subramanian, et al.
Pubblicazione: (2026)

MoralBench: Moral Evaluation of LLMs
di: Ji, Jianchao, et al.
Pubblicazione: (2024)

Big Reasoning with Small Models: Instruction Retrieval at Inference Time
di: Alkiek, Kenan, et al.
Pubblicazione: (2025)

Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders
di: Xuan, Richmond Sin Jing, et al.
Pubblicazione: (2025)

UQA: Corpus for Urdu Question Answering
di: Arif, Samee, et al.
Pubblicazione: (2024)

Exploring the psychology of LLMs' Moral and Legal Reasoning
di: Almeida, Guilherme F. C. F., et al.
Pubblicazione: (2023)

Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
di: Agarwal, Utkarsh, et al.
Pubblicazione: (2024)

Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundations
di: Nunes, José Luiz, et al.
Pubblicazione: (2024)

Histoires Morales: A French Dataset for Assessing Moral Alignment
di: Leteno, Thibaud, et al.
Pubblicazione: (2025)

Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs
di: Li, Nan, et al.
Pubblicazione: (2026)

Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers
di: Lys, Jonathan, et al.
Pubblicazione: (2026)

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
di: Yuan, Chenchen, et al.
Pubblicazione: (2025)

Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability
di: Huang, Fan, et al.
Pubblicazione: (2026)

Literary Narrative as Moral Probe : A Cross-System Framework for Evaluating AI Ethical Reasoning and Refusal Behavior
di: Flynn, David C.
Pubblicazione: (2026)

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
di: Yuan, Chenchen, et al.
Pubblicazione: (2026)

GPT-4's One-Dimensional Mapping of Morality: How the Accuracy of Country-Estimates Depends on Moral Domain
di: Strimling, Pontus, et al.
Pubblicazione: (2024)

Tracing Moral Foundations in Large Language Models
di: Yu, Chenxiao, et al.
Pubblicazione: (2026)

Mechanistic Origin of Moral Indifference in Language Models
di: Li, Lingyu, et al.
Pubblicazione: (2026)

Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test
di: Khandelwal, Aditi, et al.
Pubblicazione: (2024)

Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?
di: Jinnai, Yuu
Pubblicazione: (2024)

Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models
di: Hu, Zhibo, et al.
Pubblicazione: (2026)

Do Language Models Understand Morality? Towards a Robust Detection of Moral Content
di: Bulla, Luana, et al.
Pubblicazione: (2024)

Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning
di: Park, Jeongwoo, et al.
Pubblicazione: (2024)

Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment
di: Vida, Karina, et al.
Pubblicazione: (2024)

Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
di: Choi, Minje, et al.
Pubblicazione: (2023)

Exploring Cultural Variations in Moral Judgments with Large Language Models
di: Mohammadi, Hadi, et al.
Pubblicazione: (2025)

SaGE: Evaluating Moral Consistency in Large Language Models
di: Bonagiri, Vamshi Krishna, et al.
Pubblicazione: (2024)

Moral Mazes in the Era of LLMs
di: Nguyen, Dang, et al.
Pubblicazione: (2026)

Large Language Models as Mirrors of Societal Moral Standards
di: Papadopoulou, Evi, et al.
Pubblicazione: (2024)

Inductive Linguistic Reasoning with Large Language Models
di: Ramji, Raghav, et al.
Pubblicazione: (2024)

The Moral Consistency Pipeline: Continuous Ethical Evaluation for Large Language Models
di: Jamshidi, Saeid, et al.
Pubblicazione: (2025)

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
di: Chua, James, et al.
Pubblicazione: (2025)

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
di: Huang, Allison, et al.
Pubblicazione: (2024)

Measuring Moral LLM Responses in Multilingual Capacities
di: Basu, Kimaya, et al.
Pubblicazione: (2025)

GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning
di: Yu, Jeffy, et al.
Pubblicazione: (2024)

Morality is Contextual: Learning Interpretable Moral Contexts from Human Data with Probabilistic Clustering and Large Language Models
di: Morlat, Geoffroy, et al.
Pubblicazione: (2025)

Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective
di: Yang, Wen, et al.
Pubblicazione: (2025)

Modeling the One-to-Many Property in Open-Domain Dialogue with LLMs
di: Lee, Jing Yang, et al.
Pubblicazione: (2025)