Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling

Antal, Ainhoa Risco Patón, Teun Buijse, Peter Berck, Maarten van Gompel

Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling: 4 upvotes on Hugging Face Daily Papers, #32 of 36 papers on 2025-10-28. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.