From the 1 of 4 linked papers with an AI index.
4 papers
Studying quantization trade-offs for efficient inference deployment in machine translation
Jim Zhao, Sohir Maskey, Koen Oostermeijer +2
Deploying large language models in realistic server environments poses challenges, as the system needs to provide high-quality responses with low latency. Quantization is a common…
Accuracy and Normalized Accuracy under Length Bias: Analysis, Guidelines, and a Bayesian Alternative
Koen Oostermeijer
The paper investigates how length bias affects multiple-choice language model benchmarks, shows that normalizing scores by answer length can over-correct, and proposes a Bayesian a…
A Family of LLMs Liberated from Static Vocabularies
Aleph Alpha, :, Adnen Abdessaied +35
Tokenization is a central component of natural language processing in current large language models (LLMs), enabling models to convert raw text into processable units. Although lea…
Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models
Alex Havrilla, Andrew Dai, Laura O'Mahony +17
Synthetic data generation with Large Language Models is a promising paradigm for augmenting natural data over a nearly infinite range of tasks. Given this variety, direct compariso…