Zobrazeno 1 - 10
of 1 781
pro vyhledávání: '"A, Hagendorff"'
Autor:
Schneider, Matthias, Hagendorff, Thilo
Text-to-image models are increasingly popular and impactful, yet concerns regarding their safety and fairness remain. This study investigates the ability of ten popular Stable Diffusion models to generate harmful images, including NSFW, violent, and
Externí odkaz:
http://arxiv.org/abs/2411.15516
In an era where large language models (LLMs) are increasingly integrated into a wide range of everyday applications, research into these models' behavior has surged. However, due to the novelty of the field, clear methodological guidelines are lackin
Externí odkaz:
http://arxiv.org/abs/2409.20303
Autor:
Hagendorff, Thilo
The advent of generative artificial intelligence and the widespread adoption of it in society engendered intensive debates about its ethical implications and risks. These risks often differ from those associated with traditional discriminative machin
Externí odkaz:
http://arxiv.org/abs/2402.08323
Autor:
Meding, Kristof, Hagendorff, Thilo
Fairness in machine learning (ML) is an ever-growing field of research due to the manifold potential for harm from algorithmic discrimination. To prevent such harm, a large body of literature develops new approaches to quantify fairness. Here, we inv
Externí odkaz:
http://arxiv.org/abs/2311.06826
Autor:
Hagendorff, Thilo
Large language models (LLMs) are currently at the forefront of intertwining artificial intelligence (AI) systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady incre
Externí odkaz:
http://arxiv.org/abs/2307.16513
Autor:
Hagendorff, Thilo, Fabi, Sarah
Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Therefore, it is of great importance to evaluate their emerging abilities. In this study, we show that LLMs, most notab
Externí odkaz:
http://arxiv.org/abs/2306.07622
Autor:
Charlotte Huber, Stephan Stöbe, Andreas Hagendorff, Katja Sibylle Mühlberg, Karl-Titus Hoffmann, Berend Isermann, Rolf Wachter, Nikolaus von Dercks, Richard Schmidt, Johann Otto Pelz, Dominik Michalski
Publikováno v:
BMC Neurology, Vol 24, Iss 1, Pp 1-9 (2024)
Abstract Objective Deep vein thrombosis (DVT) is discussed as a source of embolism for cerebral ischemia in the presence of patent foramen ovale (PFO). However, previous studies reported varying rates of DVT in stroke patients, and recommendations fo
Externí odkaz:
https://doaj.org/article/8c7e88441d374b378fc5772b32fdfc6f
Autor:
Hagendorff, Thilo, Dasgupta, Ishita, Binz, Marcel, Chan, Stephanie C. Y., Lampinen, Andrew, Wang, Jane X., Akata, Zeynep, Schulz, Eric
Large language models (LLMs) show increasingly advanced emergent capabilities and are being incorporated across various societal domains. Understanding their behavior and reasoning abilities therefore holds significant importance. We argue that a fru
Externí odkaz:
http://arxiv.org/abs/2303.13988
Autor:
Hagendorff, Thilo, Fabi, Sarah
The field of artificial intelligence (AI) alignment aims to investigate whether AI technologies align with human interests and values and function in a safe and ethical manner. AI alignment is particularly relevant for large language models (LLMs), w
Externí odkaz:
http://arxiv.org/abs/2301.06859
Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Therefore, it is of great importance to evaluate their emerging abilities. In this study, we show that LLMs like GPT-3
Externí odkaz:
http://arxiv.org/abs/2212.05206