3 papers
cs.CL2025
Is There a Case for Conversation Optimized Tokenizers in Large Language Models?
Raquel Ferrando, Javier Conde, Gonzalo MartÃnez +1
The computational and energy costs of Large Language Models (LLMs) have increased exponentially driven by the growing model sizes and the massive adoption of LLMs by hundreds of mi…
cs.CL2024
Why Do Large Language Models (LLMs) Struggle to Count Letters?
Tairan Fu, Raquel Ferrando, Javier Conde +2
Large Language Models (LLMs) have achieved unprecedented performance on many complex tasks, being able, for example, to answer questions on almost any topic. However, they struggle…
cs.CL2024
Open Conversational LLMs do not know most Spanish words
Javier Conde, Miguel González, Nina Melero +5
The growing interest in Large Language Models (LLMs) and in particular in conversational models with which users can interact has led to the development of a large number of open-s…