Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Representational alignment yields generalizable safety in language models
Lingyu Li, Yan Teng, Yingchun Wang +1
Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet models remain vulnerable when the…
cs.CL2026
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Yunhao Chen, Xin Wang, Yixu Wang +6
AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior…
cs.CL2026
Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference
Wenxuan Xie, Yujia Wang, Xin Tan +3
The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning pat…