FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094217062> ?p ?o ?g. }

• W3094217062 endingPage "25" @default.
• W3094217062 startingPage "1" @default.
• W3094217062 abstract "To prevent harmful AI behavior, people need to specify constraints that forbid undesirable actions. Unfortunately, this is a complex task, since writing rules that distinguish harmful from non-harmful actions tends to be quite difficult in real-world situations. Therefore, such decisions have historically been made by a small group of powerful AI companies and developers, with limited community input. In this paper, we study how to enable a crowd of non-AI experts to work together to communicate high-quality, reliable constraints to AI systems. We first focus on understanding how humans reason about temporal dynamics in the context of AI behavior, finding through experiments on a novel game-based testbed that participants tend to adopt a long-term notion of harm, even in uncertain situations that do not affect them directly. Building off of this insight, we explore task design for long-term constraint specification, developing new filtering approaches and new methods of promoting user reflection. Next, we develop a novel rule-based interface which allows people to craft rules in an accessible fashion without programming knowledge. We test our approaches on a real-world AI problem in the domain of education, and find that our new filtering mechanisms and interfaces significantly improve constraint quality and human efficiency. We also demonstrate how these systems can be applied to other real-world AI problems (e.g. in social networks)." @default.
• W3094217062 created "2020-10-29" @default.
• W3094217062 creator A5005115899 @default.
• W3094217062 creator A5012848002 @default.
• W3094217062 creator A5013700590 @default.
• W3094217062 creator A5014247583 @default.
• W3094217062 creator A5060338610 @default.
• W3094217062 creator A5077513657 @default.
• W3094217062 creator A5089696443 @default.
• W3094217062 creator A5091434319 @default.
• W3094217062 date "2020-10-14" @default.
• W3094217062 modified "2023-09-27" @default.
• W3094217062 title "Using the Crowd to Prevent Harmful AI Behavior" @default.
• W3094217062 cites W1991486227 @default.
• W3094217062 cites W2080728202 @default.
• W3094217062 cites W2084510064 @default.
• W3094217062 cites W2093397547 @default.
• W3094217062 cites W2110151287 @default.
• W3094217062 cites W2123179704 @default.
• W3094217062 cites W2138471979 @default.
• W3094217062 cites W2147603330 @default.
• W3094217062 cites W2150250249 @default.
• W3094217062 cites W2400269077 @default.
• W3094217062 cites W2599032673 @default.
• W3094217062 cites W2856780764 @default.
• W3094217062 cites W2899260230 @default.
• W3094217062 cites W2942399136 @default.
• W3094217062 cites W2982773700 @default.
• W3094217062 cites W2986466127 @default.
• W3094217062 cites W3007662835 @default.
• W3094217062 cites W3123098919 @default.
• W3094217062 cites W3125751566 @default.
• W3094217062 cites W4288086168 @default.
• W3094217062 cites W4288086173 @default.
• W3094217062 cites W4288086175 @default.
• W3094217062 doi "https://doi.org/10.1145/3415168" @default.
• W3094217062 hasPublicationYear "2020" @default.
• W3094217062 type Work @default.
• W3094217062 sameAs 3094217062 @default.
• W3094217062 citedByCount "7" @default.
• W3094217062 countsByYear W30942170622021 @default.
• W3094217062 countsByYear W30942170622022 @default.
• W3094217062 countsByYear W30942170622023 @default.
• W3094217062 crossrefType "journal-article" @default.
• W3094217062 hasAuthorship W3094217062A5005115899 @default.
• W3094217062 hasAuthorship W3094217062A5012848002 @default.
• W3094217062 hasAuthorship W3094217062A5013700590 @default.
• W3094217062 hasAuthorship W3094217062A5014247583 @default.
• W3094217062 hasAuthorship W3094217062A5060338610 @default.
• W3094217062 hasAuthorship W3094217062A5077513657 @default.
• W3094217062 hasAuthorship W3094217062A5089696443 @default.
• W3094217062 hasAuthorship W3094217062A5091434319 @default.
• W3094217062 hasBestOaLocation W30942170621 @default.
• W3094217062 hasConcept C107457646 @default.
• W3094217062 hasConcept C111472728 @default.
• W3094217062 hasConcept C112930515 @default.
• W3094217062 hasConcept C127413603 @default.
• W3094217062 hasConcept C136764020 @default.
• W3094217062 hasConcept C138885662 @default.
• W3094217062 hasConcept C151730666 @default.
• W3094217062 hasConcept C154945302 @default.
• W3094217062 hasConcept C17744445 @default.
• W3094217062 hasConcept C199539241 @default.
• W3094217062 hasConcept C201995342 @default.
• W3094217062 hasConcept C2522767166 @default.
• W3094217062 hasConcept C2776036281 @default.
• W3094217062 hasConcept C2777363581 @default.
• W3094217062 hasConcept C2779343474 @default.
• W3094217062 hasConcept C2779530757 @default.
• W3094217062 hasConcept C2780451532 @default.
• W3094217062 hasConcept C31395832 @default.
• W3094217062 hasConcept C41008148 @default.
• W3094217062 hasConcept C71924100 @default.
• W3094217062 hasConcept C78519656 @default.
• W3094217062 hasConcept C86803240 @default.
• W3094217062 hasConceptScore W3094217062C107457646 @default.
• W3094217062 hasConceptScore W3094217062C111472728 @default.
• W3094217062 hasConceptScore W3094217062C112930515 @default.
• W3094217062 hasConceptScore W3094217062C127413603 @default.
• W3094217062 hasConceptScore W3094217062C136764020 @default.
• W3094217062 hasConceptScore W3094217062C138885662 @default.
• W3094217062 hasConceptScore W3094217062C151730666 @default.
• W3094217062 hasConceptScore W3094217062C154945302 @default.
• W3094217062 hasConceptScore W3094217062C17744445 @default.
• W3094217062 hasConceptScore W3094217062C199539241 @default.
• W3094217062 hasConceptScore W3094217062C201995342 @default.
• W3094217062 hasConceptScore W3094217062C2522767166 @default.
• W3094217062 hasConceptScore W3094217062C2776036281 @default.
• W3094217062 hasConceptScore W3094217062C2777363581 @default.
• W3094217062 hasConceptScore W3094217062C2779343474 @default.
• W3094217062 hasConceptScore W3094217062C2779530757 @default.
• W3094217062 hasConceptScore W3094217062C2780451532 @default.
• W3094217062 hasConceptScore W3094217062C31395832 @default.
• W3094217062 hasConceptScore W3094217062C41008148 @default.
• W3094217062 hasConceptScore W3094217062C71924100 @default.
• W3094217062 hasConceptScore W3094217062C78519656 @default.
• W3094217062 hasConceptScore W3094217062C86803240 @default.
• W3094217062 hasFunder F4320337389 @default.

• next