Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
Stacking Small Language Models for Generalizability
Laurence Liang
Recent advances show that large language models (LLMs) generalize strong performance across different natural language benchmarks. However, the large size of LLMs makes training an…
cs.CL2024
Scavenging Hyena: Distilling Transformers into Long Convolution Models
Tokiniaina Raharison Ralambomihanta, Shahrad Mohammadzadeh, Mohammad Sami Nur Islam +2
The rapid evolution of Large Language Models (LLMs), epitomized by architectures like GPT-4, has reshaped the landscape of natural language processing. This paper introduces a pion…