INSPIRE Lab Transforming Information Retrieval with Cutting-Edge Research

Projects

Our projects page showcases a diverse range of innovative research initiatives aimed at advancing AI, NLP, and intelligent systems. From enhancing search relevance with large language models to developing unbiased ranking systems, each project tackles real-world challenges with cutting-edge technology. Explore efforts in combating AI misinformation, personalizing user experiences through adaptive systems, leveraging graph theory for search optimization, and advancing digital security with AI forensics. These projects reflect our commitment to creating impactful, user-centric solutions that drive progress across various domains.

Graph-Based Search Personalization
Graph-Based Search Personalization Leveraging Graph Theory for Personalized Experiences

Applying graph theory to create personalized search experiences by modeling user preferences and query contexts.

AI Forensics and Authorship Attribution
AI Forensics and Authorship Attribution Identifying AI-Generated Content for Security Applications

Investigating techniques to attribute AI-generated content, advancing digital security and public safety solutions.

More

Large Language Model Enhanced Retrieval
Large Language Model Enhanced Retrieval Redefining Query Understanding in Retrieval Systems

Integrating large language models for improved query alignment and understanding, enhancing search relevance across diverse applications.

Adaptive Smart Information Systems
Adaptive Smart Information Systems Personalized and Context-Aware Data Interpretation

Developing dynamic systems that interpret, organize, and present data aligned with user intent for personalized user experiences.

Advanced Framework to Combat AI Misinformation
Advanced Framework to Combat AI Misinformation Detecting and Mitigating AI-Generated False Content

Using meta-learning and novel social prompting to detect and mitigate AI-generated misinformation and hallucinations.

Unbiased Learning and Ranking
Unbiased Learning and Ranking Fair and Equitable Recommender Systems

Exploring frameworks to eliminate biases in information retrieval and recommender systems for more equitable outcomes.