Zhiyuan Zeng

EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Precise Information Control in Long-Form Text Generation

Evaluating Large Language Models at Evaluating Instruction Following

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales