Safe GenAl for Education
Analyzing safety in LLM responses for educational tasks
Read More
Projects
Filter by Theme:
Filter by Area:
Read More
Stereotype Detection in the Indian Context (English)
A Dataset and Bias Evaluation Framework for LLMs in the Indian Context
Read More
Fairness and Accuracy in the Indian Legal Context
Incorporating Safety Through Accuracy and Fairness (InSaAF) - Checking readiness of LLMs in the Indian Legal Domain.
Read More
KAN for Enhanced Explainability and Interpretability
Generating Domain Context Grounded Natural Language Explanations for Healthcare Tasks
Read More
Evaluating Natural Language Explanations
Incorporating Safety Through Accuracy and Fairness (InSaAF) - Checking readiness of LLMs in the Indian Legal Domain.
Read More
Emotion Recognition in Conversations
Linecongraphs - Line conversation graphs for effective emotion recognition using graph neural networks.
Read More
Analyzing Fairness in Medical LMs
Incorporating Safety Through Accuracy and Fairness (InSaAF) - Checking readiness of LLMs in the Indian Legal Domain.
Read More
AI Safety & Evaluation
Coming up with evaluation frameworks and understanding model learning representations w.r.t safety
Read More
Participatory AI in AI Dev & Governance
A Principled Approach and Case Studies on Participatory AI
Read More