Sharanya Dasgupta

Sharanya Dasgupta

Data Scientist & ML Researcher Focused on LLM Safety and Reliability

View My Work

About Me

I’m a student researcher at the Indian Statistical Institute. My current focus lies on the safety, reliability, and behavior of large language models.

My research explores how these models represent knowledge, how failures arise, and how we can systematically detect and mitigate them.

Education

2023 - 2025

Master of Technology

Indian Statistical Institute

Computer and Communication Sciences Division

2019 - 2023

Bachelor of Engineering

Jadavpur University

Research & Publications

NEW

ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models

Sharanya Dasgupta, Sujoy Nath, Arkaprabha Basu, Swagatam Das

EACL Main 2026

Hallushift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs

Sujoy Nath, Arkaprabha Basu, Sharanya Dasgupta, Swagatam Das

ICVGIP Oral 2025

HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs

Sharanya Dasgupta, Sujoy Nath, Arkaprabha Basu, Pourya Shamsolmoali, Swagatam Das

IJCNN 2025

From Vigilance to Veracity: Hallucination Detection, Mitigation, and Safety Enhancement in Large Language Models

Sharanya Dasgupta

Master’s Thesis

Industry Experience

InfoEdge (naukri.com)

Data Scientist

Jul 2025 - Present

Data Science Intern

May 2024 - Jul 2024
  • Built the Apply Prediction model to forecast application volume from job attributes and provide actionable recommendations to optimize job descriptions.
  • Worked on Salary Estimation model using multivariate outlier detection and regression, improving compensation transparency.

Get In Touch

I'm always open to discussing new research opportunities and collaborations.