news
| Oct 04, 2026 | Our paper IndicSafeEval: Evaluating Persuasion-Based Jailbreak Vulnerabilities in Indic Languages has been accepted at EMNLP 2026 (Findings). (Saikat Mondal, Deeksha Varshney, Oana Cocarascu, Asif Ekbal). Check it out on [arXiv]. |
|---|---|
| Jul 04, 2026 | Our paper MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models has been published at the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026). (Rishabh Makwana, Deeksha Varshney, Oana Cocarascu). Check it out on [ACL Anthology]. |
| Mar 20, 2026 | Our paper Indic-TunedLens: Interpreting Multilingual Models in Indian Languages has been accepted at the 13th Workshop on NLP for Similar Languages, Varieties and Dialects in Rabat, Morocco. (M. Panchal, D. Varshney, Mamta, A. Ekbal). Check it out on [ACL Anthology]. |
| Nov 17, 2025 | Our work Protein Secondary Structure Prediction Using 3D Graphs and Relation-Aware Message Passing Transformers is now available on arXiv. (D. Varshney, S. Garg, S. Tyagi, D. Varshney, N. Deep, A. Ekbal). Check it out on [arXiv]. |
| Nov 15, 2025 | Our work Concept-Based Interpretability for Toxicity Detection is now available on arXiv. (S. Garg, D. Singh, D. Varshney, Mamta). Check it out on [arXiv]. |
| Nov 09, 2025 | Our paper Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation has been accepted at EMNLP 2025. (K. Ong, R. Mao, D. Varshney, P. P. Liang, E. Cambria, G. Mengaldo). Check it out on [EMNLP]. |