11-17 One fish, two fish, but not the whole sea: Alignment reduces language models’ conceptual diversity
11-17 The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News
11-17 TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation
11-17 TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System