Gallery

Presented poster "Towards Robust and Trustworthy NLP Systems"

Presented two papers at VarDial: "Improving Dialect Robustness in Large Language Models via LoRA and Mixture-of-Experts" and "Indic-TunedLens: Interpreting Multilingual Models in Indian Languages"

Presented "I-GUARD: Interpretability-Guided Parameter Optimization for Adversarial Defense"

Presented "FactEval: Evaluating the Robustness of Fact Verification Systems in the Era of Large Language Models" (My first paper as Dr. Mamta.)

Presented "BiasWipe: Mitigating Unintended Bias in Text Classifiers through Model Interpretability"

Presented "Elevating Code-mixed Text Handling through Auditory Information of Words"

Presented "Service is Good, Very Good or Excellent? Towards Aspect-Based Sentiment Intensity Analysis" (my first international travel.)