1. 'From Complexity to Clarity: Transforming Chest X-ray Reports with Chained Prompting', AAAI 2025 Student Abstract
2. 'HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs', IJCNN 2025
3. 'HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs', ICVGIP 2025 (Preprint coming soon)
4. 'Hallucination Mitigation & Safety Alignment in LLMs' (Title Representational), Under Review, ACL ARR
Research Experience
1. Research Assistant, Present, Indian Institute of Technology (IIT), Delhi, Laboratory of Computational Social Systems (LCS2), working on an Agentic AI project in collaboration with Microsoft Research India (MSRI), focusing on enhancing the safety and reasoning capabilities of AI agents.
2. Research Collaborator, June 2024 - June 2025, Indian Statistical Institute (ISI), ECSU, supervised by Dr. Swagatam Das, developed a novel approach for detecting factual hallucinations in LLM outputs and created a simplified medical report generation system.
Education
Indian Institute of Technology (IIT), Delhi, currently working at LCS2, co-supervised by Prof. Tanmoy Chakraborty and Dr. Akshay Nambi from Microsoft Research India (MSRI).
Background
Research Interests: Trustworthy AI systems, LLM interpretability and safety, agentic reasoning, and AI applications in healthcare. Areas of expertise: Natural Language Processing, Multimodal AI Systems.