4 papers
Code Roulette: How Prompt Variability Affects LLM Code Generation
Andrei Paleyes, Radzim Sendyka, Diana Robinson +2
Code generation is one of the most active areas of application of Large Language Models (LLMs). While LLMs lower barriers to writing code and accelerate development process, the ov…
Optimising for Energy Efficiency and Performance in Machine Learning
Emile Dos Santos Ferreira, Andrei Paleyes, Neil D. Lawrence
The ubiquity of machine learning (ML) and the demand for ever-larger models bring an increase in energy consumption and environmental impact. However, little is known about the ene…
Machine Learning Systems: A Survey from a Data-Oriented Perspective
Christian Cabrera, Andrei Paleyes, Pierre Thodoroff +1
Engineers are deploying ML models as parts of real-world systems with the upsurge of AI technologies. Real-world environments challenge the deployment of such systems because these…
LLM Performance for Code Generation on Noisy Tasks
Radzim Sendyka, Christian Cabrera, Andrei Paleyes +2
This paper investigates the ability of large language models (LLMs) to recognise and solve tasks which have been obfuscated beyond recognition. Focusing on competitive programming…