all AI news
Optimal Design for Human Feedback
April 23, 2024, 4:42 a.m. | Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari, Aniket Deshmukh, Ge Liu, Yifei Ma, Branislav Kveton
cs.LG updates on arXiv.org arxiv.org
Abstract: Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by this progress, and the cost of obtaining high-quality human annotations, we study the problem of data collection for learning preference models. The key idea in our work is to generalize optimal designs, a tool for computing efficient data logging policies, to ranked lists. To show the generality of our ideas, we study both absolute and relative feedback …
abstract advances annotations artificial artificial intelligence arxiv collection cost cs.lg data data collection design designs feedback human human feedback intelligence key progress quality study the key type work
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
1 day, 4 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
1 day, 4 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York