3 papers
cs.CL2025
Prompt Balance Matters: Understanding How Imbalanced Few-Shot Learning Affects Multilingual Sense Disambiguation in LLMs
Deshan Sumanathilaka, Nicholas Micallef, Julian Hough
Recent advances in Large Language Models (LLMs) have significantly reshaped the landscape of Natural Language Processing (NLP). Among the various prompting techniques, few-shot pro…
cs.CL2025
IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages
Deshan Sumanathilaka, Isuri Anuradha, Ruvan Weerasinghe +2
The paper overviews the shared task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages. It focuses on the reverse transliteration of low-resourced languages in…
cs.CL2024
Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation
T. G. D. K. Sumanathilaka, Nicholas Micallef, Julian Hough
Ambiguous words are often found in modern digital communications. Lexical ambiguity challenges traditional Word Sense Disambiguation (WSD) methods, due to limited data. Consequentl…