Authority Before Utility: Non-Compensatory Control for Persistent LLM Memory
Quick summary
arXiv:2609.37474v1 Announce Type: new Abstract: Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion, or revocation makes it inadmissible for the current answer. We formalize this as a separation between utility and authority. A fixed finite penalty applied to an unnormalized utility score cannot guarantee exclusion under arbitrary positive-affine reparameterization of that score; by contrast, rank-normalized compensation is scale-invariant and therefore forms a stronger empirical comparator. Our
Key takeaways
- arXiv:2609.37474v1 Announce Type: new Abstract: Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion, or revocation makes it inadmissible for the current answer.
- We formalize this as a separation between utility and authority.
- A fixed finite penalty applied to an unnormalized utility score cannot guarantee exclusion under arbitrary positive-affine reparameterization of that score; by contrast, rank-normalized compensation is scale-invariant and therefore forms a stronger empirical comparator.
Why it matters
“Authority Before Utility: Non-Compensatory Control for Persistent LLM Memory” is a product decision that may change how people work with AI. Its value depends on task completion, correction effort and data handling—not simply the presence of a new feature.
Member comments