Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Roosta, Tanya"'
Large Language Models (LLMs) attempt to imitate human behavior by responding to humans in a way that pleases them, including by adhering to their values. However, humans come from diverse cultures with different values. It is critical to understand w
Externí odkaz:
http://arxiv.org/abs/2406.14805
Autor:
Dammu, Preetam Prabhu Srikar, Naidu, Himanshu, Dewan, Mouly, Kim, YoungMin, Roosta, Tanya, Chadha, Aman, Shah, Chirag
In the midst of widespread misinformation and disinformation through social media and the proliferation of AI-generated texts, it has become increasingly difficult for people to validate and trust information they encounter. Many fact-checking approa
Externí odkaz:
http://arxiv.org/abs/2403.09724
Autor:
Amirizaniani, Maryam, Yao, Jihan, Lavergne, Adrian, Okada, Elizabeth Snell, Chadha, Aman, Roosta, Tanya, Shah, Chirag
As Large Language Models (LLMs) become more pervasive across various users and scenarios, identifying potential issues when using these models becomes essential. Examples of such issues include: bias, inconsistencies, and hallucination. Although audi
Externí odkaz:
http://arxiv.org/abs/2402.09346
As Large Language Models (LLMs) are integrated into various sectors, ensuring their reliability and safety is crucial. This necessitates rigorous probing and auditing to maintain their effectiveness and trustworthiness in practical applications. Subj
Externí odkaz:
http://arxiv.org/abs/2402.09334
Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue; however, the c
Externí odkaz:
http://arxiv.org/abs/2311.04142
Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investigation demonstrates th
Externí odkaz:
http://arxiv.org/abs/2205.01557
Autor:
Dupuy, Christophe, Roosta, Tanya G., Long, Leo, Chung, Clement, Gupta, Rahul, Avestimehr, Salman
Federated Learning (FL) applied to real world data may suffer from several idiosyncrasies. One such idiosyncrasy is the data distribution across devices. Data across devices could be distributed such that there are some "heavy devices" with large amo
Externí odkaz:
http://arxiv.org/abs/2202.03925
Training neural machine translation (NMT) models in federated learning (FL) settings could be inefficient both computationally and communication-wise, due to the large size of translation engines as well as the multiple rounds of updates required to
Externí odkaz:
http://arxiv.org/abs/2112.06135
Autor:
Roosta, Tanya G.1 roosta@eecs.berkeley.edu, Wainwright, Martin J.2 wainwrig@eecs.berkeley.edu, Sastry, Shankar S.1 sastty@eecs.berkeley.edu
Publikováno v:
IEEE Transactions on Signal Processing. Sep2008, Vol. 56 Issue 9, p4293-4305. 13p. 6 Graphs.
Publikováno v:
Proceedings of the First ACM Conference: Wireless Network Security; 3/31/2008, p100-108, 9p