AIConfPaper
← Search

Avani Gupta

4 accepted papers

2025

Building Trust in Clinical LLMs: Bias Analysis and Dataset Transparency

Svetlana Maslenkova, Clement Christophe, Marco AF Pimentel, Tathagata Raha, Muhammad Umar Salman, Ahmed Al Mahrooqi +4
EMNLP 2025

Large language models offer transformative potential for healthcare, yet their responsible and equitable development depends critically on a deeper understanding of how training data characteristics influence model behavior, including the potential for bias. Current practices in dataset curation and

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Prototype Guided Backdoor Defense via Activation Space Manipulation

Venkat Adithya Amula, Sunayana Samavedam, Saurabh Saini, Avani Gupta, P J Narayanan
ICCV 2025accepted

Deep learning models are susceptible to backdoor attacks involving malicious perturbation of some training data with a trigger to force misclassification to a target class. Various triggers have been used including semantic triggers that are easily realizable. We present Prototype Guided Backd…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement

Avani Gupta, Saurabh Saini, P J Narayanan
NeurIPS 2023poster

Humans use abstract *concepts* for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Concept Activation Vectors (CAVs) estimate a model's sensitivity and possible biases to a given concept. We extend CAVs f…

Cited by 6Source ↗PDF ↗Scholar ↗