4 papers · 1 filter
Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals
Lei Zhao, Qichao Zhao, Bowen Zuo +1
On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully understood. Across code generat…
A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning
Mengqi Li, Lei Zhao, Anthony Man-Cho So +2
Can a language model improve reasoning by learning from its own imperfect responses, without rewards or teacher-provided solutions? We present Self-evolving Post-Training (SePT), a…
StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
Qijun Luo, Mengqi Li, Lei Zhao +1
Training language models on long sequence data is a demanding requirement for enhancing the model's capability on complex tasks, e.g., long-chain reasoning. However, as the sequenc…
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
Xingwu Chen, Lei Zhao, Difan Zou
Despite the remarkable success of transformer-based models in various real-world tasks, their underlying mechanisms remain poorly understood. Recent studies have suggested that tra…