Publications

Jump to

• Human-centered AI framework for overdose mortality surveillance [AJPH 2026]
• Consistency Is the Key: Detecting Hallucinations in LLMs [IJCNLP-AACL 2025]
• An algorithmic recipe to construct Lyapunov functions [ANZCC 2024]

Human-centered artificial intelligence framework for overdose mortality surveillance

American Journal of Public Health, 2026

Karli Hochstatter, Smaranda Muresan, Raavi Gupta, Talia Nadel, Anubhav Jangra, Yuxin Li, Cecilia Yang, Nicole D'Anna, Hannah Johnson, Jan Gryczynski, Nabila El-Bassel, Jason Graham

A human-centered AI framework for overdose mortality surveillance using Medicolegal Death Investigation reports.

Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts

Findings of IJCNLP-AACL, Mumbai, India, 2025

Raavi Gupta, Pranav Hari Panicker, Sumit Bhatia, Ganesh Ramakrishnan

CONFACTCHECK detects hallucinations in LLM outputs by checking consistency of responses to factual probes, with no external knowledge base required.

An algorithmic recipe to construct Lyapunov functions for continuous vector fields

Australian & New Zealand Control Conference (ANZCC), Gold Coast, Australia, 2024

S. Chattopadhyay, Raavi Gupta, P. Paruchuri, Debasish Chatterjee

A computationally feasible approach to construct Lyapunov functions for equilibria of nonlinear continuous vector fields, requiring no special algebraic structure.