Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning

24 February 2025

Papers citing "Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning"

1 / 1 papers shown

Title
SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization Huashan Sun Shengyi Liao Yansen Han Yu Bai Chong Feng ... Weizhou Shen Fanqi Wan Ming Yan Junzhe Zhang Fei Huang 20 0 0 16 May 2025