Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Chenruo, Tang, Kenan, Qin, Yao, Lei, Qi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.22829
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909626493042688
author Liu, Chenruo
Tang, Kenan
Qin, Yao
Lei, Qi
author_facet Liu, Chenruo
Tang, Kenan
Qin, Yao
Lei, Qi
contents This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types connections between specific causes of distribution shift and fine-grained AI safety issues: (1) methods addressing a specific shift type can help achieve corresponding safety goals, or (2) certain shifts and safety issues can be formally reduced to each other, enabling mutual adaptation of their methods. Our findings provide a unified perspective that encourages fundamental integration between distribution shift and AI safety research.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22829
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
Liu, Chenruo
Tang, Kenan
Qin, Yao
Lei, Qi
Machine Learning
Artificial Intelligence
This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types connections between specific causes of distribution shift and fine-grained AI safety issues: (1) methods addressing a specific shift type can help achieve corresponding safety goals, or (2) certain shifts and safety issues can be formally reduced to each other, enabling mutual adaptation of their methods. Our findings provide a unified perspective that encourages fundamental integration between distribution shift and AI safety research.
title Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.22829