A Storage-Retrieval Gap in Parametric Knowledge Graph Memory
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
A Storage-Retrieval Gap in Parametric Knowledge Graph Memory released — as an alternative to graph RAG, presents an approach that compiles a knowledge graph offline into a bank of LoRA adapters, one per entity, and uses it as a parametric knowledge layer. Reports that on MetaQA the adapters hold factual knowledge that generalizes to new questions, gaining +0.243 on single-valued relations over a baseline that knows almost nothing, while the adapters of neighboring entities do not contain the answer — so stored knowledge is not retrieved by similarity, and the correlation between weight geometry and subgraph semantics is only ρ=+0.329
Why it matters
Opens a parametric knowledge-graph strand that, unlike the GraphRAG lineage, which queries the graph at retrieval time, compiles the graph into model weights in advance — while at the same time pinning down that this strand's bottleneck is not storage but adapter selection (routing). The authors conclude that the remaining task is to find an adapter-selection mechanism that goes beyond semantic similarity. Figures are as reported by the authors.
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2608.25489Added in Week 36, 2026 · See that week
On the map — ㉑ Graph Engineering line
- Previous stopMAGG
- This recordA Storage-Retrieval Gap in Parametric Knowledge Graph Memory
- Next stopAgent Zero Memory