Projects
Government-sponsored initiatives, enterprise LLM safety benchmarks, and adaptive multi-agent frameworks built at RespAI Lab.
Funded Research Initiatives
1 Project
Machine Unlearning
Government of India (SERB) sponsored initiative (₹30.5 Lakh) investigating algorithmic data removal and privacy compliance in deep learning models without performance degradation. Successfully completed on January 1, 2026.
Core Research & Open Benchmarks
3 Projects
OrgAccess
A Benchmark for Role-Based Access Control in Organization-Scale LLMs — testing whether models can reliably respect organizational roles, permissions, and access boundaries.
Pedagogical LLM Agents
Adaptive Teacher and Student Multi-Agent Simulation: Genetic Policy Adaptation Meets Persona-based Retrieval Augmented Generation (Accepted at EMNLP 2025).
Right Prediction, Wrong Reasoning
Uncovering LLM Misalignment in Rheumatoid Arthritis Disease Diagnosis: AI models can achieve high classification accuracy while generating clinically flawed medical explanations.
Production Systems & Web Platforms
1 Project
FormBharlo
Har Sarkari Bharti, Ek Jagah — A high-performance full-stack recruitment portal offering real-time government job alerts, active application tracking, and exam utility tools.