Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
Anhao Zhao, Junlong Tong, Yingqi Fan +3
Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo esti…
cs.LG2026
GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
Yuyang Bai, Zhuofeng Li, Ping Nie +2
Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organized as heterogeneous graphs rather than…