Towards Explainable Food Hazard Detection
Published:
A neuro-symbolic approach to food hazard detection that combines Large Language Models (Llama-3.1-8B) with knowledge graphs (ConceptNet) to create an inherently explainable classification system.
Portfolio
Chat with My Research: A Conversational RAG Application
Published:
An interactive RAG-powered web application that allows users to ask questions about my NLP research paper, built with Streamlit, LangChain, and Google Gemini.
AI Research Assistant: A Multi-Document Agentic RAG System
Published:
An advanced agentic system that can read, compare, and synthesize information across multiple documents to answer complex, comparative questions about my research. 
Argumentative Structure Analysis for Domain Adaptation
Published:
My Master’s Thesis project where I created a novel annotated dataset of conversational arguments, engineered a graph-based representation, and benchmarked LLM performance for relation classification.