no code implementations • 14 Mar 2024 • Balaji Ganesan, Matheen Ahmed Pasha, Srinivasa Parkala, Neeraj R Singh, Gayatri Mishra, Sumit Bhatia, Hima Patel, Somashekar Naganna, Sameep Mehta
Explaining neural model predictions to users requires creativity.
no code implementations • 27 Feb 2024 • Shubh Goyal, Medha Hira, Shubham Mishra, Sukriti Goyal, Arnav Goel, Niharika Dadu, Kirushikesh DB, Sameep Mehta, Nishtha Madaan
Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns.
no code implementations • 15 Aug 2023 • Sandeep Singamsetty, Nishtha Madaan, Sameep Mehta, Varad Bhatnagar, Pushpak Bhattacharyya
To help combat this problem, we have created a comprehensive pipeline consisting of a half-truth detection model and a claim editing model.
no code implementations • 1 Jun 2023 • Rahul Madhavan, Rishabh Garg, Kahini Wadhawan, Sameep Mehta
Our experiments show that CFL achieves such a detoxification without much impact on the model perplexity.
no code implementations • 12 Aug 2021 • Nitin Gupta, Hima Patel, Shazia Afzal, Naveen Panwar, Ruhi Sharma Mittal, Shanmukha Guttula, Abhinav Jain, Lokesh Nagalapatti, Sameep Mehta, Sandeep Hans, Pranay Lohia, Aniya Aggarwal, Diptikalyan Saha
We attempt to re-look at the data quality issues in the context of building a machine learning pipeline and build a tool that can detect, explain and remediate issues in the data, and systematically and automatically capture all the changes applied to the data.
no code implementations • 10 Dec 2020 • Balaji Ganesan, Hima Patel, Sameep Mehta
Contact Tracing has been used to identify people who were in close proximity to those infected with SARS-Cov2 coronavirus.
no code implementations • 14 Oct 2020 • Shazia Afzal, Rajmohan C, Manish Kesarwani, Sameep Mehta, Hima Patel
Data exploration and quality analysis is an important yet tedious process in the AI pipeline.
no code implementations • 18 Jan 2020 • Karan Dabas, Nishtha Madan, Vijay Arya, Sameep Mehta, Gautam Singh, Tanmoy Chakraborty
To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic.
13 code implementations • 3 Oct 2018 • Rachel K. E. Bellamy, Kuntal Dey, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilovic, Seema Nagar, Karthikeyan Natesan Ramamurthy, John Richards, Diptikalyan Saha, Prasanna Sattigeri, Moninder Singh, Kush R. Varshney, Yunfeng Zhang
Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking.
no code implementations • 12 Sep 2018 • Rashmi Nagpal, Chetna Wadhwa, Mallika Gupta, Samiulla Shaikh, Sameep Mehta, Vikram Goyal
Automatic extraction of fairness policies, or in general, any specific kind of policies from large legal corpus can be very useful for the study of bias and fairness in the context of AI applications.
no code implementations • 22 Aug 2018 • Matthew Arnold, Rachel K. E. Bellamy, Michael Hind, Stephanie Houde, Sameep Mehta, Aleksandra Mojsilovic, Ravi Nair, Karthikeyan Natesan Ramamurthy, Darrell Reimer, Alexandra Olteanu, David Piorkowski, Jason Tsay, Kush R. Varshney
We envision such documents to contain purpose, performance, safety, security, and provenance information to be completed by AI service providers for examination by consumers.
no code implementations • 25 Jul 2018 • Nishtha Madaan, Sameep Mehta, Shravika Mittal, Ashima Suvarna
The presence of gender stereotypes in many aspects of society is a well-known phenomenon.
1 code implementation • 11 Apr 2018 • Nishtha Madaan, Gautam Singh, Sameep Mehta, Aditya Chetan, Brihi Joshi
Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically.
1 code implementation • 2 Feb 2018 • Deepak Vijaykeerthy, Anshuman Suri, Sameep Mehta, Ponnurangam Kumaraguru
Deep neural networks (DNNs) are vulnerable to malicious inputs crafted by an adversary to produce erroneous outputs.
no code implementations • 20 Nov 2017 • Manish Kesarwani, Bhaskar Mukhoty, Vijay Arya, Sameep Mehta
In this work, we present a cloud-based extraction monitor that can quantify the extraction status of models by observing the query and response streams of both individual and colluding adversarial users.
no code implementations • 11 Oct 2017 • Nishtha Madaan, Sameep Mehta, Mayank Saxena, Aditi Aggarwal, Taneea S Agrawaal, Vrinda Malhotra
In this work, we have worked with movie data from Wikipedia plots and movie trailers from YouTube.
no code implementations • 11 Jul 2017 • Atul Kumar, Sameep Mehta
Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc.
no code implementations • 10 Jul 2017 • Suranjana Samanta, Sameep Mehta
Our algorithm works best for the datasets which have sub-categories within each of the classes of examples.