Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| 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 |