Zobrazeno 1 - 10
of 94
pro vyhledávání: '"A, Zalmanovici"'
Autor:
Kour, George, Zwerdling, Naama, Zalmanovici, Marcel, Anaby-Tavor, Ateret, Fandina, Ora Nova, Farchi, Eitan
Large language models (LLMs) are increasingly used in business dialogue systems but they pose security and ethical risks. Multi-turn conversations, where context influences the model's behavior, can be exploited to produce undesired responses. In thi
Externí odkaz:
http://arxiv.org/abs/2409.04822
Large Language Models (LLMs) are used for many tasks, including those related to coding. An important aspect of being able to utilize LLMs is the ability to assess their fitness for specific usages. The common practice is to evaluate LLMs against a s
Externí odkaz:
http://arxiv.org/abs/2407.19772
Autor:
Achintalwar, Swapnaja, Garcia, Adriana Alvarado, Anaby-Tavor, Ateret, Baldini, Ioana, Berger, Sara E., Bhattacharjee, Bishwaranjan, Bouneffouf, Djallel, Chaudhury, Subhajit, Chen, Pin-Yu, Chiazor, Lamogha, Daly, Elizabeth M., DB, Kirushikesh, de Paula, Rogério Abreu, Dognin, Pierre, Farchi, Eitan, Ghosh, Soumya, Hind, Michael, Horesh, Raya, Kour, George, Lee, Ja Young, Madaan, Nishtha, Mehta, Sameep, Miehling, Erik, Murugesan, Keerthiram, Nagireddy, Manish, Padhi, Inkit, Piorkowski, David, Rawat, Ambrish, Raz, Orna, Sattigeri, Prasanna, Strobelt, Hendrik, Swaminathan, Sarathkrishna, Tillmann, Christoph, Trivedi, Aashka, Varshney, Kush R., Wei, Dennis, Witherspooon, Shalisha, Zalmanovici, Marcel
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be
Externí odkaz:
http://arxiv.org/abs/2403.06009
Autor:
Kour, George, Zalmanovici, Marcel, Zwerdling, Naama, Goldbraich, Esther, Fandina, Ora Nova, Anaby-Tavor, Ateret, Raz, Orna, Farchi, Eitan
As large language models become more prevalent, their possible harmful or inappropriate responses are a cause for concern. This paper introduces a unique dataset containing adversarial examples in the form of questions, which we call AttaQ, designed
Externí odkaz:
http://arxiv.org/abs/2311.04124
Autor:
Ackerman, Samuel, Anaby-Tavor, Ateret, Farchi, Eitan, Goldbraich, Esther, Kour, George, Rabinovich, Ella, Raz, Orna, Route, Saritha, Zalmanovici, Marcel, Zwerdling, Naama
Conversational systems or chatbots are an example of AI-Infused Applications (AIIA). Chatbots are especially important as they are often the first interaction of clients with a business and are the entry point of a business into the AI (Artificial In
Externí odkaz:
http://arxiv.org/abs/2204.13043
Testing Machine Learning (ML) models and AI-Infused Applications (AIIAs), or systems that contain ML models, is highly challenging. In addition to the challenges of testing classical software, it is acceptable and expected that statistical ML models
Externí odkaz:
http://arxiv.org/abs/2112.11832
Publikováno v:
Originally published in proceedings of Engineering Dependable and Secure Machine Learning Systems (EDSMLS) workshop at AAAI 2019 conference
Classifiers and other statistics-based machine learning (ML) techniques generalize, or learn, based on various statistical properties of the training data. The assumption underlying statistical ML resulting in theoretical or empirical performance gua
Externí odkaz:
http://arxiv.org/abs/2111.05672
Consider a structured dataset of features, such as $\{\textrm{SEX}, \textrm{INCOME}, \textrm{RACE}, \textrm{EXPERIENCE}\}$. A user may want to know where in the feature space observations are concentrated, and where it is sparse or empty. The existen
Externí odkaz:
http://arxiv.org/abs/2110.05430
Publikováno v:
International Workshop on Engineering Dependable and Secure Machine Learning Systems, at EDSMLS 2020
Machine learning (ML) solutions are prevalent. However, many challenges exist in making these solutions business-grade. One major challenge is to ensure that the ML solution provides its expected business value. In order to do that, one has to bridge
Externí odkaz:
http://arxiv.org/abs/2108.05620
Publikováno v:
DeepTest workshop of ICSE, 2021
Detecting drift in performance of Machine Learning (ML) models is an acknowledged challenge. For ML models to become an integral part of business applications it is essential to detect when an ML model drifts away from acceptable operation. However,
Externí odkaz:
http://arxiv.org/abs/2108.05319