2 citations · 2 across the 4 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CL2023
Learning to Skip for Language Modeling
Dewen Zeng, Nan Du, Tao Wang +4
Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning. However, most language models allocate the same amount of…
cs.LG2023★ 2 cited
Controlled Decoding from Language Models
Sidharth Mudgal, Jong Lee, Harish Ganapathy +10
KL-regularized reinforcement learning (RL) is a popular alignment framework to control the language model responses towards high reward outcomes. We pose a tokenwise RL objective a…