4 papers
AdaptBPE: From General Purpose to Specialized Tokenizers
Vijini Liyanage, François Yvon
Subword tokenization methods, such as Byte-Pair Encoding (BPE), significantly impact the performance and efficiency of large language models (LLMs). The standard approach involves…
An Ensemble Method Based on the Combination of Transformers with Convolutional Neural Networks to Detect Artificially Generated Text
Vijini Liyanage, Davide Buscaldi
Thanks to the state-of-the-art Large Language Models (LLMs), language generation has reached outstanding levels. These models are capable of generating high quality content, thus m…
A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications
Vijini Liyanage, Davide Buscaldi, Adeline Nazarenko
Automatic text generation based on neural language models has achieved performance levels that make the generated text almost indistinguishable from those written by humans. Despit…
A Multi-language Platform for Generating Algebraic Mathematical Word Problems
Vijini Liyanage, Surangika Ranathunga
Existing approaches for automatically generating mathematical word problems are deprived of customizability and creativity due to the inherent nature of template-based mechanisms t…