Team: Mandira Sawkar, Omar Khursheed, Dr. Ashique KhudaBukhsh
Summary: Developing NLP pipeline over 200 years of Hansard debates (1803–2005) using LLMs to study gender bias, framing, and speaker dynamics. Applying representation analysis and framing detection to uncover temporal shifts in discourse, generating insights for bias and fairness in AI systems.
Team: Mandira Sawkar
Resources: [Code]
Summary: Developed a theoretical framework consisting of multiple LLM agents producing verifiable responses through debate and consensus.
My contribution: Sole contributor.
Team: Mandira Sawkar, Leona Joseph, Vivek Senthil
Resources: [Code]
Summary: Designed a logic-gated fact-checking system integrating RoBERTa classifiers with contradiction detection, validated on 7,200+ claims. Improved explainability and reliability by maintaining 83% accuracy while enabling selective overrides for low-confidence predictions.
My contribution: Conducted extensive literature review and developed a framework with a fine-tuned DistilRoBERTa with logic-gated overrides; Co-authored an ACM-style conference paper.
Team: Mandira Sawkar
Resources: [Code]
Summary: Developed an AI framework with LLMs (GPT API, fine-tuning, chain-of-thought reasoning) to evaluate 200+ Supreme Court cases, revealing how factors such as panel size, prompting strategies, and ideology personas influence alignment between LLM reasoning and human judges.
My contribution: Sole contributor.
Team: Mandira Sawkar, Leona Joseph, Shrid Pant
Resources: [Code]
Summary: Created a theoretical hybrid model for fair jury selection and intra-jury deliberation using optimization and game theory with a novel extension to nash equilibrium.
My contribution: Conducted literature review and helped develop both the optimization and game theoretic components; Co-presented and won 1st place at the RIT Graduate Showcase.
Team: Mandira Sawkar
Resources: [Code]
Summary: Built a SparkML RandomForest classifier to predict the police-precinct of ticketed vehicles using the NYC parking-ticket dataset. Used PySpark for parallel computation. Achieved 98% accuracy, and identified police precincts with anomalous ticketing practices.
My contribution: Sole contributor.
Team: Mandira Sawkar
Resources: [Code]
Summary: Created a RandomForest model to predict issues in the product supplychain which might delay product shipment to customers. Employed PCA and LDA optimization for visualization and dimension reduction. RandomForest model achieved accuracy of 97% (with PCA) and 92% (with LDA).
My contribution: Sole contributor.
Team: Mandira Sawkar
Resources: [Code]
Summary: Trained a Voting Classifier to predict cancer type with the Wisconsin Breast Cancer Dataset. Hosted the model as a Flask-based microservice running within a Docker container.
My contribution: Sole contributor.
Team: Mandira Sawkar
Resources: [Code]
Summary: Created a SparkML RandomForest model to predict total employee compensation. Queried data with SparkSQL, ran PySpark scripts to run EDA, pre-process data, and train model achieving with 0.98 R2 score.
My contribution: Sole contributor.