Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity

arXiv:2507.00657 · cs.HC, cs.AI, cs.SI · Submitted 2025-07-01 · Read on arXiv

cs.HC, cs.AI, cs.SI

Submitted: 2025-07-01

Updated: 2025-07-01

Terminology

• Consistency — 3× in this paper · explained in 3 episodes
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes
• Polarization — 1× in this paper · explained in 2 episodes

Related papers

• Calibrating LLM Explanations to Human Decisions with Reinforcement Learning
• Rethinking Opinion Measurement Interfaces for Human-in-the-Loop Optimization
• EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning
• EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
• HAGI++: Head-Assisted Gaze Imputation and Generation
• Explanation User Interfaces: A Systematic Literature Review