2 citations · 2 across the 5 of their papers we have counts for
6 papers
AutoAdapt: Automatic Domain Discovery Enables Low-Cost Extensibility
Josh McGiff, Salma Mekaoui, Robert Shanahan +1
Instruction-tuned models are deployed into environments where domains are heterogeneous and evolve, yet adding new domains or data typically requires costly retraining. We present…
SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters
Josh McGiff, Salma Mekaoui, Robert Shanahan +1
Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved practical ch…
Irish-BLiMP: A Linguistic Benchmark for Evaluating Human and Language Model Performance in a Low-Resource Setting
Josh McGiff, Khanh-Tung Tran, William Mulcahy +7
We present Irish-BLiMP (Irish Benchmark of Linguistic Minimal Pairs), the first dataset and framework designed for fine-grained evaluation of linguistic competence in the Irish lan…
SemiAdapt and SemiLoRA: Efficient Domain Adaptation for Transformer-based Low-Resource Language Translation with a Case Study on Irish
Josh McGiff, Nikola S. Nikolov
Fine-tuning is widely used to tailor large language models for specific tasks such as neural machine translation (NMT). However, leveraging transfer learning is computationally exp…
Overcoming Data Scarcity in Generative Language Modelling for Low-Resource Languages: A Systematic Review
Josh McGiff, Nikola S. Nikolov
Generative language modelling has surged in popularity with the emergence of services such as ChatGPT and Google Gemini. While these models have demonstrated transformative potenti…
Bridging the gap in online hate speech detection: a comparative analysis of BERT and traditional models for homophobic content identification on X/Twitter
Josh McGiff, Nikola S. Nikolov
Our study addresses a significant gap in online hate speech detection research by focusing on homophobia, an area often neglected in sentiment analysis research. Utilising advanced…