169 citations · 227 across the 13 of their papers we have counts for
15 papers
Improving Diversity in LLM Short Story Generation
Zahra Solati Dehkordi, Vasileios Lampos
Large language models (LLMs) can generate accurate responses, but these are void of diversity. We attempt to address this for the task of creative short story generation. Drawing o…
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
Minoo Kim, Vasileios Lampos, George Drayson
Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a trigger appears in the input. Existing backdoor defences for LL…
From Jumps to Signatures: a Generative Method for Temporal Point Processes
Niels Cariou-Kotlarek, Vasileios Lampos
Rough path signatures are a universal feature map for continuous paths and, via the expected signature, characterise path distributions. These guarantees do not directly extend to…
Machine-generated text detection prevents language model collapse
George Drayson, Emine Yilmaz, Vasileios Lampos
As Large Language Models (LLMs) become increasingly prevalent, their generated outputs are proliferating across the web, risking a future where machine-generated content dilutes hu…
DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting
Yuxuan Shu, Vasileios Lampos
In multivariable time series (MTS) forecasting, existing state-of-the-art deep learning approaches tend to focus on autoregressive formulations and often overlook the potential of…
Unsupervised hard Negative Augmentation for contrastive learning
Yuxuan Shu, Vasileios Lampos
We present Unsupervised hard Negative Augmentation (UNA), a method that generates synthetic negative instances based on the term frequency-inverse document frequency (TF-IDF) retri…