3 papers
cs.CY2026
Simple Role Assignment is Extraordinarily Effective for Safety Alignment
Zhou Ziheng, Jiakun Ding, Zhaowei Zhang +6
Principle-based alignment often lacks context sensitivity and completeness. Grounded in Theory of Mind, we propose role conditioning as a compact alternative: social roles (e.g., m…
cs.CL2026
BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models
Junyu Zhang, Yipeng Kang, Jiong Guo +2
Do large language models (LLMs) genuinely understand abstract concepts, or merely manipulate them as statistical patterns? We introduce an abstraction-grounding framework that deco…
cs.HC2021
Reinforced Natural Language Interfaces via Entropy Decomposition
Xiaoran Wu, Yipeng Kang
In this paper, we study the technical problem of developing conversational agents that can quickly adapt to unseen tasks, learn task-specific communication tactics, and help listen…