๐Ÿ“–
What should AI forget? A design and taxonomy for negative space governance in AI memory
Eryue Xu, Ke Ding, Ting-Yu Chang, Tianshi Li, Masooda Bashir

What should AI forget? A design and taxonomy for negative space governance in AI memory

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

AI memory personalizes assistants, yet users want some disclosed information forgotten. We characterize the negative space of AI memory, where protection should take precedence over potential future personalization benefits. From 179 incidents reported by 146 users, we developed a taxonomy of 15 information categories users want excluded from memory, revealing sensitivity concerns beyond conventional taxonomies. We operationalize this taxonomy in FENCE, a policy-level memory gate that automatically applies user-selected category-based rules to subsequent conversations, preventing information from protected conversations from entering AI memory by default while allowing case-by-case overrides. In a within-subjects study (N=15), participants described FENCE as making memory governance more usable, interpretable, and trustworthy than conventional post-hoc management. Our findings demonstrate how taxonomy-based rules can potentially support user-defined memory boundaries. We call for collective efforts to establish policies governing what AI should not remember, rather than leaving protection to individual retrospective management.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title What should AI forget? A design and taxonomy for negative space governance in AI memory
Author / Organization Eryue Xu, Ke Ding, Ting-Yu Chang, Tianshi Li, Masooda Bashir
Subject & Discipline cs.HC
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-271312
Original Source Link Visit Source Page on arxiv.org »