5 papers
Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism
Tairan Fu, Gonzalo MartÃnez, Javier Conde +4
The execution of Large Language Models (LLMs) has been shown to produce nondeterministic results when run on Graphics Processing Units (GPUs), even when they are configured to prod…
Concurrent Linguistic Error Detection (CLED): a New Methodology for Error Detection in Large Language Models
Jinhua Zhu, Javier Conde, Zhen Gao +3
The wide adoption of Large language models (LLMs) makes their dependability a pressing concern. Detection of errors is the first step to mitigating their impact on a system and thu…
Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)
Ziheng Wang, Pedro Reviriego, Farzad Niknia +4
Stochastic computing (SC) has emerged as an efficient low-power alternative for deploying neural networks (NNs) in resource-limited scenarios, such as the Internet of Things (IoT).…
Speed and Conversational Large Language Models: Not All Is About Tokens per Second
Javier Conde, Miguel González, Pedro Reviriego +3
The speed of open-weights large language models (LLMs) and its dependency on the task at hand, when run on GPUs, is studied to present a comparative analysis of the speed of the mo…
Can ChatGPT Learn to Count Letters?
Javier Conde, Gonzalo MartÃnez, Pedro Reviriego +3
Large language models (LLMs) struggle on simple tasks such as counting the number of occurrences of a letter in a word. In this paper, we investigate if ChatGPT can learn to count…