SOURCE-LINKED INTELLIGENCE

Beyond Endpoint Scores: Time- and Capacity-Conditioned Evaluation of Continual Knowledge Updating

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Continual knowledge-updating methods are often declared superior from one final checkpoint and one conventional adapter rank. We show that this can be insufficient to identify the better operating point. Holding a periodic hierarchy fixed, we compare it with cumulative replay over a 24-month Wikidata stream while varying evaluation month, replay LoRA rank, and query formulation. The apparent winner changes across this region: on Qwen2.5-1.5B, the hierarchy's 5.0-point advantage over rank-8 replay becomes an 11.6-point deficit against rank-72 replay, and at high ranks a consolidation-aligned en

Read original source ↗ Open in workspace

recordType

paper

region

Global