Imagen de Portada

Disentangling the Drivers of LLM Social Conformity: An Uncertainty-Moderated Dual-Process Mechanism

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhong, Huixin, Liu, Yanan, Cao, Qi, Wang, Shijin, Ye, Zijing, Wang, Zimu, Zhang, Shiyao
Formato:	Preprint
Publicado:	2025
Materias:	Computers and Society Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Unified Uncertainty Estimation for Cognitive Diagnosis Models
por: Wang, Fei, et al.
Publicado: (2024)

Regulating AI: Applying insights from behavioural economics and psychology to the application of article 5 of the EU AI Act
por: Zhong, Huixin, et al.
Publicado: (2023)

Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
por: Ye, Jinyi, et al.
Publicado: (2026)

Optimizing Student Ability Assessment: A Hierarchy Constraint-Aware Cognitive Diagnosis Framework for Educational Contexts
por: Sun, Xinjie, et al.
Publicado: (2024)

Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning
por: Celona, Luigi, et al.
Publicado: (2024)

Conformity and Social Impact on AI Agents
por: Bellina, Alessandro, et al.
Publicado: (2026)

GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation
por: Zhong, Hailin, et al.
Publicado: (2025)

Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations
por: Fidone, Giacomo, et al.
Publicado: (2025)

PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
por: Kachwala, Zoher, et al.
Publicado: (2026)

Gender Bias of LLM in Economics: An Existentialism Perspective
por: Zhong, Hui, et al.
Publicado: (2024)

LLM-Assisted Replication for Quantitative Social Science
por: Kubota, So, et al.
Publicado: (2026)

Community Moderation and the New Epistemology of Fact Checking on Social Media
por: Augenstein, Isabelle, et al.
Publicado: (2025)

What Is Actually Being Annotated? Inter-Prompt Reliability as a Measurement Problem in LLM-Based Social Science Labeling
por: Liu, Jingyuan
Publicado: (2026)

Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment
por: Kwon, Jea, et al.
Publicado: (2025)

Social World Model-Augmented Mechanism Design Policy Learning
por: Zhang, Xiaoyuan, et al.
Publicado: (2025)

Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
por: Xiao, Tong, et al.
Publicado: (2024)

Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
por: Hu, Yueqing, et al.
Publicado: (2026)

CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
por: Ye, Wanghao, et al.
Publicado: (2025)

Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare
por: Shi, Zhengliang, et al.
Publicado: (2025)

Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach
por: Qin, Xiaoyou, et al.
Publicado: (2026)

LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities
por: Gurcan, Onder
Publicado: (2024)

Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
por: Wang, Bingchen, et al.
Publicado: (2025)

Artificial Intelligence and Dual Contract
por: Qi, Qian
Publicado: (2023)

A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver Behavior
por: Bhattacharyya, Raunak P., et al.
Publicado: (2020)

Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events
por: Liu, Mengzhu, et al.
Publicado: (2025)

Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
por: Zhang, Jintian, et al.
Publicado: (2023)

Disentangling Heterogeneous Knowledge Concept Embedding for Cognitive Diagnosis on Untested Knowledge
por: Zhang, Miao, et al.
Publicado: (2024)

Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph
por: Tang, Zhenheng, et al.
Publicado: (2026)

A Multi-Level Strategy for Deepfake Content Moderation under EU Regulation
por: Förster, Max-Paul, et al.
Publicado: (2025)

Knowing Your Uncertainty -- On the application of LLM in social sciences
por: Zhang, Bolun, et al.
Publicado: (2025)

Reflections on Disentanglement and the Latent Space
por: Schaerf, Ludovica
Publicado: (2024)

Exploring Social Desirability Response Bias in Large Language Models: Evidence from GPT-4 Simulations
por: Lee, Sanguk, et al.
Publicado: (2024)

The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process
por: Carichon, Florian, et al.
Publicado: (2025)

Speculations on Uncertainty and Humane Algorithms
por: Gray, Nicholas
Publicado: (2024)

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
por: Yang, Shujian, et al.
Publicado: (2025)

RoboBuddy in the Classroom: Exploring LLM-Powered Social Robots for Storytelling in Learning and Integration Activities
por: Tozadore, Daniel, et al.
Publicado: (2025)

A Detailed Study on LLM Biases Concerning Corporate Social Responsibility and Green Supply Chains
por: Ontrup, Greta, et al.
Publicado: (2025)

Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Models
por: Wang, Zhenyu, et al.
Publicado: (2024)

Do LLM-Driven Agents Exhibit Engagement Mechanisms? Controlled Tests of Information Load, Descriptive Norms, and Popularity Cues
por: Peng, Tai-Quan, et al.
Publicado: (2026)

Content Moderation by LLM: From Accuracy to Legitimacy
por: Huang, Tao
Publicado: (2024)