LIMEADE: From AI Explanations to Advice Taking

March 09, 2020 Β· Declared Dead Β· πŸ› ACM Trans. Interact. Intell. Syst.

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Benjamin Charles Germain Lee, Doug Downey, Kyle Lo, Daniel S. Weld arXiv ID 2003.04315 Category cs.IR: Information Retrieval Cross-listed cs.LG, stat.ML Citations 9 Venue ACM Trans. Interact. Intell. Syst. Last Checked 4 months ago
Abstract
Research in human-centered AI has shown the benefits of systems that can explain their predictions. Methods that allow an AI to take advice from humans in response to explanations are similarly useful. While both capabilities are well-developed for transparent learning models (e.g., linear models and GA$^2$Ms), and recent techniques (e.g., LIME and SHAP) can generate explanations for opaque models, little attention has been given to advice methods for opaque models. This paper introduces LIMEADE, the first general framework that translates both positive and negative advice (expressed using high-level vocabulary such as that employed by post-hoc explanations) into an update to an arbitrary, underlying opaque model. We demonstrate the generality of our approach with case studies on seventy real-world models across two broad domains: image classification and text recommendation. We show our method improves accuracy compared to a rigorous baseline on the image classification domains. For the text modality, we apply our framework to a neural recommender system for scientific papers on a public website; our user study shows that our framework leads to significantly higher perceived user control, trust, and satisfaction.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted