| Title: | Predictable artificial intelligence |
|---|
| Authors: | ID Zhou, Lexin (Author)
ID Casares, Pablo A. M. (Author)
ID Martínez-Plumed, Fernando (Author)
ID Burden, John (Author)
ID Burnell, Ryan (Author)
ID Cheke, Lucy (Author)
ID Ferri, Cèsar (Author)
ID Marcoci, Alexandru (Author)
ID Mehrbakhsh, Behzad (Author)
ID Moros-Daval, Yael (Author)
ID Rutar, Danaja (Author) |
|---|
| Files: |  RAZ_Zhou_Lexin_2026.pdf (4,86 MB)
MD5: 01E78DFB20707B7A4BA7EEAAFDDF1502
 https://www.sciencedirect.com/science/article/pii/S0004370226000172
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FAMNIT - Faculty of Mathematics, Science and Information Technologies
|
|---|
| Abstract: | Many areas of artificial intelligence, and machine learning in particular, aim at being probably correct, i.e., valid on average, rather than pursuing the idealistic goal of being provably valid for all inputs. However, AI systems could still be predictably valid, such as an imperfect robot deliverer for which we can reliably and precisely predict the task instances for which it is correct and safe, its valid operating range. “Predictable AI” is a nascent research area that explores ways of anticipating key validity indicators (e.g., performance, safety) of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI, and thus should be prioritised over performance. We formally characterise predictability, explore its most relevant components, illustrate what can be predicted, describe alternative candidates for predictors, as well as the trade-offs between maximising validity and predictability. To illustrate these concepts, we bring an array of illustrative examples covering diverse ecosystem configurations. “Predictable AI” is related to other areas of technical and non-technical AI research, but have distinctive questions, hypotheses, techniques and challenges. This paper aims to elucidate them, calls for identifying paths towards a landscape of predictably valid AI systems and outlines the potential impact of this emergent field. |
|---|
| Keywords: | predictable AI, general-purpose AI, AI safety |
|---|
| Publication date: | 30.01.2026 |
|---|
| Year of publishing: | 2026 |
|---|
| Number of pages: | str. 1-21 |
|---|
| Numbering: | Vol. 353, article 104491 |
|---|
| PID: | 20.500.12556/RUP-22641  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 1872-7921 |
|---|
| DOI: | 10.1016/j.artint.2026.104491 |
|---|
| COBISS.SI-ID: | 267372803 |
|---|
| Publication date in RUP: | 09.02.2026 |
|---|
| Views: | 42 |
|---|
| Downloads: | 2 |
|---|
| Metadata: |    |
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
