Publications

STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks

Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization

Towards Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric

Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces

Polarity-Aware Probing for Quantifying Latent Alignment in Language Models

CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning

Rethinking Explainability in the Era of Multimodal AI

A Graph Talks, But Who’s Listening? Rethinking Evaluations for Graph-Language Models

CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare

The Multilingual Mind: A Survey of Multilingual Reasoning in Language Models

EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding

HALLUCINOGEN: Benchmarking Hallucination in Implicit Reasoning within Large Vision Language Models

Analyzing Memorization in Large Language Models through the Lens of Model Attribution

Towards Operationalizing Right to Data Protection

On the Impact of Fine-tuning on Chain-of-Thought Reasoning

Quantifying Uncertainty in Natural Language Explanations of Large Language Models

Towards Safe Large Language Models for Medicine

Understanding the Effects of Iterative Prompting on Truthfulness

Certifying LLM Safety Against Adversarial Prompting

OpenXAI: Towards a Transparent Evaluation of Post hoc Model Explanations

Estimating Example Difficulty Using Variance of Gradients

Evaluating Explainability for Graph Neural Networks

DeAR: Debiasing Vision-Language Models with Additive Residuals

GNNDelete: A General Strategy for Unlearning in Graph Neural Networks

Explaining RL Decisions with Trajectories

Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation