all AI news
Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for System Improvement
Nov. 24, 2022, 12:27 a.m. | Allen Institute for AI
Allen Institute for AI www.youtube.com
Our goal is a teachable reasoning system for question-answering (QA), where a user can interact with faithful answer explanations, and correct its errors so that the system improves over time. Our approach is to augment a QA model with a dynamic memory of user feedback, containing user-supplied corrections to erroneous model beliefs that users identify during interaction. Retrievals from memory are used as additional context for QA, to help avoid previous mistakes in similar new …
More from www.youtube.com / Allen Institute for AI
Towards a more contextualized view of the web
4 days, 12 hours ago |
www.youtube.com
Optimization within Latent Spaces
4 days, 17 hours ago |
www.youtube.com
Training Human-AI Teams
4 days, 19 hours ago |
www.youtube.com
LMQL Programming Large Language Models
3 weeks, 3 days ago |
www.youtube.com
Does Generative AI Infringe Copyright?
3 weeks, 5 days ago |
www.youtube.com
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Machine Learning Engineer - Sr. Consultant level
@ Visa | Bellevue, WA, United States