2 papers
cs.AI2025
Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation
Chenkai Sun, Denghui Zhang, ChengXiang Zhai +1
Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understand…
cs.CL2025
Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models
Yuheng Wu, Wentao Guo, Zirui Liu +3
This paper investigates the emergence of Theory-of-Mind (ToM) capabilities in large language models (LLMs) from a mechanistic perspective, focusing on the role of extremely sparse…