Zobrazeno 1 - 10
of 59 844
pro vyhledávání: '"Harms P"'
Autor:
Ovalle, Anaelia, Pavasovic, Krunoslav Lehman, Martin, Louis, Zettlemoyer, Luke, Smith, Eric Michael, Williams, Adina, Sagun, Levent
Natural-language assistants are designed to provide users with helpful responses while avoiding harmful outputs, largely achieved through alignment to human preferences. Yet there is limited understanding of whether alignment techniques may inadverte
Externí odkaz:
http://arxiv.org/abs/2411.03700
Large language models (LLMs) are increasingly integrated into a variety of writing tasks. While these tools can help people by generating ideas or producing higher quality work, like many other AI tools they may risk causing a variety of harms, dispr
Externí odkaz:
http://arxiv.org/abs/2410.00906
Recommender systems have become integral to digital experiences, shaping user interactions and preferences across various platforms. Despite their widespread use, these systems often suffer from algorithmic biases that can lead to unfair and unsatisf
Externí odkaz:
http://arxiv.org/abs/2409.06916
Eye tracking technology offers great potential for improving road safety. It is already being built into vehicles, namely cars and trucks. When this technology is integrated into transit service vehicles, employees, i.e., bus drivers, will be subject
Externí odkaz:
http://arxiv.org/abs/2410.24131
Recent years have seen increased awareness of the potential significant impacts of computing technologies, both positive and negative. This whitepaper explores how to address possible harmful consequences of computing technologies that might be diffi
Externí odkaz:
http://arxiv.org/abs/2408.06431
Autor:
Leidinger, Alina, Rogers, Richard
With the widespread availability of LLMs since the release of ChatGPT and increased public scrutiny, commercial model development appears to have focused their efforts on 'safety' training concerning legal liabilities at the expense of social impact
Externí odkaz:
http://arxiv.org/abs/2407.11733
Autor:
Abercrombie, Gavin, Benbouzid, Djalel, Giudici, Paolo, Golpayegani, Delaram, Hernandez, Julio, Noro, Pierre, Pandit, Harshvardhan, Paraschou, Eva, Pownall, Charlie, Prajapati, Jyoti, Sayre, Mark A., Sengupta, Ushnish, Suriyawongkul, Arthit, Thelot, Ruby, Vei, Sofia, Waltersdorfer, Laura
This paper introduces a collaborative, human-centred taxonomy of AI, algorithmic and automation harms. We argue that existing taxonomies, while valuable, can be narrow, unclear, typically cater to practitioners and government, and often overlook the
Externí odkaz:
http://arxiv.org/abs/2407.01294
Generative artificial intelligence models, when trained on a sufficient number of a person's images, can replicate their identifying features in a photorealistic manner. We refer to this process as 'likeness generation'. Likeness-featuring synthetic
Externí odkaz:
http://arxiv.org/abs/2407.12030
Though research into text-to-image generators (T2Is) such as Stable Diffusion has demonstrated their amplification of societal biases and potentials to cause harm, such research has primarily relied on computational methods instead of seeking informa
Externí odkaz:
http://arxiv.org/abs/2408.01594
Large language models (LLMs) are now being considered and even deployed for applications that support high-stakes decision-making, such as recruitment and clinical decisions. While several methods have been proposed for measuring bias, there remains
Externí odkaz:
http://arxiv.org/abs/2408.01285