6 papers
To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech
Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri
Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checkin…
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks
Saikat Mondal, Mamta, Deeksha Varshney +2
Large language models (LLMs) are increasingly used in multilingual settings, yet their safety is still evaluated primarily in English. This limits our understanding of how alignmen…
MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models
Rishabh Makwana, Mamta, Deeksha Varshney +1
Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge. While prior work has shown that s…
Indic-TunedLens: Interpreting Multilingual Models in Indian Languages
Mihir Panchal, Deeksha Varshney, Mamta +1
Multilingual large language models (LLMs) are increasingly deployed in linguistically diverse regions like India, yet most interpretability tools remain tailored to English. Prior…
Concept-Based Interpretability for Toxicity Detection
Samarth Garg, Divya Singh, Deeksha Varshney +1
The rise of social networks has not only facilitated communication but also allowed the spread of harmful content. Although significant advances have been made in detecting toxic l…
Elevating Code-mixed Text Handling through Auditory Information of Words
Mamta, Zishan Ahmad, Asif Ekbal
With the growing popularity of code-mixed data, there is an increasing need for better handling of this type of data, which poses a number of challenges, such as dealing with spell…