c2023-ripple-edits-erroneous-change-rate

IN premise — summaries/2026/08/24/cohen-2023-ripple-effects-s6-conclusion-and-discussion.md

Created 2026-08-25T02:57:57+00:00

In ≥ 68% of cases across all settings, factual editing via KE methods introduces erroneous changes (noise or abstention) rather than simply making no change

Summary

Most attempts to surgically correct a single fact in a language model end up causing real collateral damage, not just a clean update. This means any system that relies on knowledge editing should expect side effects in roughly seven out of ten cases and budget verification steps to catch the noise or newly introduced refusals before they propagate.