Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bosch, Antal van den, Patón, Ainhoa Risco, Buijse, Teun, Berck, Peter, van Gompel, Maarten
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.22317
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911231427739648
author Bosch, Antal van den
Patón, Ainhoa Risco
Buijse, Teun
Berck, Peter
van Gompel, Maarten
author_facet Bosch, Antal van den
Patón, Ainhoa Risco
Buijse, Teun
Berck, Peter
van Gompel, Maarten
contents We present memory-based language modeling as an efficient, eco-friendly alternative to deep neural network-based language modeling. It offers log-linearly scalable next-token prediction performance and strong memorization capabilities. Implementing fast approximations of k-nearest neighbor classification, memory-based language modeling leaves a relatively small ecological footprint both in training and in inference mode, as it relies fully on CPUs and attains low token latencies. Its internal workings are simple and fully transparent. We compare our implementation of memory-based language modeling, OLIFANT, with GPT-2 and GPT-Neo on next-token prediction accuracy, estimated emissions and speeds, and offer some deeper analyses of the model.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22317
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling
Bosch, Antal van den
Patón, Ainhoa Risco
Buijse, Teun
Berck, Peter
van Gompel, Maarten
Computation and Language
We present memory-based language modeling as an efficient, eco-friendly alternative to deep neural network-based language modeling. It offers log-linearly scalable next-token prediction performance and strong memorization capabilities. Implementing fast approximations of k-nearest neighbor classification, memory-based language modeling leaves a relatively small ecological footprint both in training and in inference mode, as it relies fully on CPUs and attains low token latencies. Its internal workings are simple and fully transparent. We compare our implementation of memory-based language modeling, OLIFANT, with GPT-2 and GPT-Neo on next-token prediction accuracy, estimated emissions and speeds, and offer some deeper analyses of the model.
title Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling
topic Computation and Language
url https://arxiv.org/abs/2510.22317