Qwen

The 'Qwen' dataset/benchmark is used to evaluate the safety of search queries generated by reinforcement learning-trained language models, particularly in the context of their alignment with instruction-tuned models.

Papers using Qwen (3)

Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning2025Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training2025Achieving Scalable Robot Autonomy Via Neurosymbolic Planning Using Lightweight Local LLM2025