Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Hilgard, Sophie"'
Autor:
Wojcik, Stefan, Hilgard, Sophie, Judd, Nick, Mocanu, Delia, Ragain, Stephen, Hunzaker, M. B. Fallin, Coleman, Keith, Baxter, Jay
We present an approach for selecting objectively informative and subjectively helpful annotations to social media posts. We draw on data from on an online environment where contributors annotate misinformation and simultaneously rate the contribution
Externí odkaz:
http://arxiv.org/abs/2210.15723
Autor:
Epstein, Ziv, Foppiani, Nicolò, Hilgard, Sophie, Sharma, Sanjana, Glassman, Elena, Rand, David
Social media platforms are increasingly deploying complex interventions to help users detect false news. Labeling false news using techniques that combine crowd-sourcing with artificial intelligence (AI) offers a promising way to inform users about p
Externí odkaz:
http://arxiv.org/abs/2112.03450
As machine learning models are increasingly used in critical decision-making settings (e.g., healthcare, finance), there has been a growing emphasis on developing methods to explain model predictions. Such \textit{explanations} are used to understand
Externí odkaz:
http://arxiv.org/abs/2106.12563
Counterfactual explanations are emerging as an attractive option for providing recourse to individuals adversely impacted by algorithmic decisions. As they are deployed in critical applications (e.g. law enforcement, financial lending), it becomes im
Externí odkaz:
http://arxiv.org/abs/2106.02666
Ranking algorithms are being widely employed in various online hiring platforms including LinkedIn, TaskRabbit, and Fiverr. Prior research has demonstrated that ranking algorithms employed by these platforms are prone to a variety of undesirable bias
Externí odkaz:
http://arxiv.org/abs/2012.00423
As black box explanations are increasingly being employed to establish model credibility in high-stakes settings, it is important to ensure that these explanations are accurate and reliable. However, prior work demonstrates that explanations generate
Externí odkaz:
http://arxiv.org/abs/2008.05030
Machine learning is a powerful tool for predicting human-related outcomes, from credit scores to heart attack risks. But when deployed, learned models also affect how users act in order to improve outcomes, whether predicted or real. The standard app
Externí odkaz:
http://arxiv.org/abs/2006.11638
As machine learning black boxes are increasingly being deployed in domains such as healthcare and criminal justice, there is growing emphasis on building tools and techniques for explaining these black boxes in an interpretable manner. Such explanati
Externí odkaz:
http://arxiv.org/abs/1911.02508
Autor:
Idreos, Stratos, Dayan, Niv, Qin, Wilson, Akmanalp, Mali, Hilgard, Sophie, Ross, Andrew, Lennon, James, Jain, Varun, Gupta, Harshita, Li, David, Zhu, Zichen
We introduce the concept of design continuums for the data layout of key-value stores. A design continuum unifies major distinct data structure designs under the same model. The critical insight and potential long-term impact is that such unifying mo
Externí odkaz:
http://arxiv.org/abs/1907.05443
When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy. Here we propose a framework to directly support
Externí odkaz:
http://arxiv.org/abs/1905.12686