Safety, alignment & interpretability· survey· 2018
A Survey Of Methods For Explaining Black Box Models
On the reading lists
- #17 on the Surveys & tutorials shelf (2026 edition)
Why it matters
Comprehensive early survey of explanation methods.
Condensed from the expert lists' notes.
The record
- First released
- 2018 (from arXiv 1802.01933)
- Citations
- 5,433 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.