PUBLICATIONS / 02
My research explores how language models interpret what we give them, and how we can evaluate their responses.
01
Nov 2025
PromptRefine
14th EAI ArtsIT Conference · Dubai, UAE
A framework that refines vague, ambiguous, or biased prompts before they reach LLMs. Evaluated across OpenAI and Anthropic models for clarity, intent alignment, and bias mitigation.
02
Dec 2024
To BI or not To BI?
5th International Conference on Computers and AI Technology (CAIT 2024) · Hangzhou, China
An evaluation of deep learning and transformer models for suicidal ideation detection, accepted at CAIT 2024. BERT achieved 98.6% accuracy in the study, outperforming the LSTM-CNN and Bi-LSTM-CNN baselines evaluated.
Interested in the work? Get in touch to discuss the research.