2 papers
cs.CL2026
Hybrid Policy Distillation for LLMs
Wenhong Zhu, Ruobing Xie, Rui Wang +1
Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimiz…
cs.CL2024
LLMCRIT: Teaching Large Language Models to Use Criteria
Weizhe Yuan, Pengfei Liu, Matthias Gallé
Humans follow criteria when they execute tasks, and these criteria are directly used to assess the quality of task completion. Therefore, having models learn to use criteria to pro…