Zobrazeno 1 - 10
of 131
pro vyhledávání: '"Das, Soumi"'
Autor:
Speicher, Till, Khan, Mohammad Aflah, Wu, Qinyuan, Nanda, Vedant, Das, Soumi, Ghosh, Bishwamittra, Gummadi, Krishna P., Terzi, Evimaria
Understanding whether and to what extent large language models (LLMs) have memorised training data has important implications for the reliability of their output and the privacy of their training data. In order to cleanly measure and disentangle memo
Externí odkaz:
http://arxiv.org/abs/2407.19262
Autor:
Wu, Qinyuan, Khan, Mohammad Aflah, Das, Soumi, Nanda, Vedant, Ghosh, Bishwamittra, Kolling, Camila, Speicher, Till, Bindschaedler, Laurent, Gummadi, Krishna P., Terzi, Evimaria
We propose an approach for estimating the latent knowledge embedded inside large language models (LLMs). We leverage the in-context learning (ICL) abilities of LLMs to estimate the extent to which an LLM knows the facts stored in a knowledge base. Ou
Externí odkaz:
http://arxiv.org/abs/2404.12957
Autor:
Das, Soumi, Nag, Shubhadip, Sharma, Shreyyash, Bhattacharya, Suparna, Bhattacharya, Sourangshu
Trustworthy AI is crucial to the widespread adoption of AI in high-stakes applications with fairness, robustness, and accuracy being some of the key trustworthiness metrics. In this work, we propose a controllable framework for data-centric trustwort
Externí odkaz:
http://arxiv.org/abs/2403.05174
Targeted model poisoning attacks pose a significant threat to federated learning systems. Recent studies show that edge-case targeted attacks, which target a small fraction of the input space are nearly impossible to counter using existing fixed defe
Externí odkaz:
http://arxiv.org/abs/2305.02022
Data valuation and subset selection have emerged as valuable tools for application-specific selection of important training data. However, the efficiency-accuracy tradeoffs of state-of-the-art methods hinder their widespread application to many AI wo
Externí odkaz:
http://arxiv.org/abs/2203.06814
Autor:
Das, Soumi, Singh, Arshdeep, Chatterjee, Saptarshi, Bhattacharya, Suparna, Bhattacharya, Sourangshu
Finding valuable training data points for deep neural networks has been a core research challenge with many applications. In recent years, various techniques for calculating the "value" of individual training datapoints have been proposed for explain
Externí odkaz:
http://arxiv.org/abs/2104.13794
Autor:
Das, Soumi, Patibandla, Harikrishna, Bhattacharya, Suparna, Bera, Kshounis, Ganguly, Niloy, Bhattacharya, Sourangshu
Training vision-based Urban Autonomous driving models is a challenging problem, which is highly researched in recent times. Training such models is a data-intensive task requiring the storage and processing of vast volumes of (possibly redundant) dri
Externí odkaz:
http://arxiv.org/abs/2103.13021
Autor:
Das, Soumi, Kalava, Rajath Nandan, Kumar, Kolli Kiran, Kandregula, Akhil, Suhaas, Kalpam, Bhattacharya, Sourangshu, Ganguly, Niloy
Travel time estimation is a fundamental problem in transportation science with extensive literature. The study of these techniques has intensified due to availability of many publicly available large trip datasets. Recently developed deep learning ba
Externí odkaz:
http://arxiv.org/abs/1911.02623
Publikováno v:
In Dyes and Pigments October 2023 218
Publikováno v:
In Journal of Cardiothoracic and Vascular Anesthesia January 2023 37(1):16-22