Imagen de Portada

Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pagan, Nicolò, Barrie, Christopher, Bail, Chris Andrew, Törnberg, Petter
Formato:	Preprint
Publicado:	2026
Materias:	Social and Information Networks Artificial Intelligence Computation and Language Computers and Society Multiagent Systems
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Computational Turing Test Reveals Systematic Differences Between Human and AI Language
por: Pagan, Nicolò, et al.
Publicado: (2025)

MASim: Multilingual Agent-Based Simulation for Social Science
por: Zhang, Xuan, et al.
Publicado: (2025)

Online Homogeneity Can Emerge Without Filtering Algorithms or Homophily Preferences
por: Törnberg, Petter
Publicado: (2025)

Modeling Earth-Scale Human-Like Societies with One Billion Agents
por: Guan, Haoxiang, et al.
Publicado: (2025)

Form Without Function: Agent Social Behavior in the Moltbook Network
por: Zerhoudi, Saber, et al.
Publicado: (2026)

Credibility Governance: A Social Mechanism for Collective Self-Correction under Weak Truth Signals
por: He, Wanying, et al.
Publicado: (2026)

LLM-Based Social Simulations Require a Boundary
por: Wu, Zengqing, et al.
Publicado: (2025)

Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content
por: Mushtaq, Abdullah, et al.
Publicado: (2025)

Collaborative governance of cyber violence: A two-phase, multi-scenario four-party evolutionary game and SBI1I2R public opinion dissemination
por: Yang, Xiaoting, et al.
Publicado: (2025)

Carthago Delenda Est: Co-opetitive Indirect Information Diffusion Model for Influence Operations on Online Social Media
por: Low, Jwen Fai, et al.
Publicado: (2024)

A Hate Speech Moderated Chat Application: Use Case for GDPR and DSA Compliance
por: Fillies, Jan, et al.
Publicado: (2024)

Large Language Models can Achieve Social Balance
por: Cisneros-Velarde, Pedro
Publicado: (2024)

Network Effects and Agreement Drift in LLM Debates
por: Cau, Erica, et al.
Publicado: (2026)

Misinformation Dissemination: Effects of Network Density in Segregated Communities
por: Karimi, Soroush, et al.
Publicado: (2024)

Sync or Sink: Bounds on Algorithmic Collective Action with Noise and Multiple Groups
por: Karan, Aditya, et al.
Publicado: (2025)

Emergent LLM behaviors are observationally equivalent to data leakage
por: Barrie, Christopher, et al.
Publicado: (2025)

Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation
por: Larooij, Maik, et al.
Publicado: (2025)

Leveraging LLM-based agents for social science research: insights from citation network simulations
por: Ji, Jiarui, et al.
Publicado: (2025)

Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
por: Kumar, Shivani, et al.
Publicado: (2026)

Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective
por: Gabison, Garry A., et al.
Publicado: (2025)

AI-Gram: When Visual Agents Interact in a Social Network
por: Shin, Andrew
Publicado: (2026)

Steering the Herd: A Framework for LLM-based Control of Social Learning
por: Arghal, Raghu, et al.
Publicado: (2025)

Law in Silico: Simulating Legal Society with LLM-Based Agents
por: Wang, Yiding, et al.
Publicado: (2025)

When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms
por: Ren, Qibing, et al.
Publicado: (2025)

Stronger together? The homophily trap in networks
por: Oliveira, Marcos, et al.
Publicado: (2024)

An Agentic Evaluation Architecture for Historical Bias Detection in Educational Textbooks
por: Stefan, Gabriel, et al.
Publicado: (2026)

Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
por: Tang, Zichen, et al.
Publicado: (2026)

Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics
por: De Nobili, Cristiano
Publicado: (2026)

I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
por: Campedelli, Gian Maria, et al.
Publicado: (2024)

When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis
por: Dietrich, Juergen
Publicado: (2026)

Dynamics of Affective Polarization: From Consensus to Partisan Divides
por: Nettasinghe, Buddhika, et al.
Publicado: (2024)

APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents
por: Zheng, Quan, et al.
Publicado: (2026)

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
por: Yang, Shiyi, et al.
Publicado: (2025)

Realistic gossip in Trust Game on networks: the GODS model
por: Majewski, Jan, et al.
Publicado: (2025)

Food4All: A Multi-Agent Framework for Real-time Free Food Discovery with Integrated Nutritional Metadata
por: Yuan, Zhengqing, et al.
Publicado: (2025)

Reimagining Urban Science: Scaling Causal Inference with Large Language Models
por: Xia, Yutong, et al.
Publicado: (2025)

Emergent Social Intelligence Risks in Generative Multi-Agent Systems
por: Huang, Yue, et al.
Publicado: (2026)

AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research
por: Xia, Tong, et al.
Publicado: (2025)

Embodied LLM Agents Learn to Cooperate in Organized Teams
por: Guo, Xudong, et al.
Publicado: (2024)

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
por: Zhu, Kunlun, et al.
Publicado: (2025)