Bhavik Chandna

According to our database, Bhavik Chandna authored at least 4 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective.

Bhavik Chandna, Zubair Bashir, Procheta Sen

CoRR, June, 2025

XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content.

Vadivel Abishethvarman, Bhavik Chandna, Pratik Jalan, Usman Naseem

CoRR, June, 2025

ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content.

Bhavik Chandna, Mariam Aboujenane, Usman Naseem

CoRR, March, 2025

2024

A Counterfactual Explanation Framework for Retrieval Models.

Bhavik Chandna, Procheta Sen

CoRR, 2024