Jiazhan Feng

Reverse-Engineered Reasoning for Open-Ended Generation

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

COIG-Writer: A High-Quality Chinese Creative Writing with Thought Process Dataset

WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions

Synergistic Information Retrieval: Interplay between Search and Large Language Models