knowledge-routing-faithfulness-validated
OUT derived (depth 3)
Created 2026-08-25T03:05:14+00:00 · Reviewed 2026-08-25T04:28:09+00:00
The parametric/contextual two-channel knowledge architecture is a genuine computational duality rather than a surface-level re-ranking bias, because retrieval context demonstrably inverts the parametric accuracy trend (accuracy increases with document relevance for rare facts) and BM25 recall remains robust independently of parametric scaling.
Justifications
SL — The routing claim (depth-2) requires the faithfulness validation (depth-1) to exclude the confound that the model merely re-ranks provided text; the trend inversion is the causal signature of a separate reading pathway.
Antecedents (all must be IN):
- OUT knowledge-routing-architecture — The LLM implements a natural knowledge-routing architecture: well-supported facts are parametrically stored in local MLP key-value memory (head of the distribution), while rare/long-tail facts are architecturally routed through the contextual channel (retrieval, extended context windows), with the routing boundary determined by corpus document frequency rather than an arbitrary design choice.
- IN context-faithfulness-evidence — The model genuinely reads and uses provided context (not merely re-ranking retrieval) because accuracy scales with document-relevance count even when BM25 recall shows only mild dependence on the same variable.
Dependents
These beliefs depend on this one:
- OUT context-trend-as-geometric-convergence-in-practice — The industry trajectory of expanding context windows (200K tokens), agentic tooling, and multi-hour autonomous runs is the operational convergence toward the theoretically-predicted "complete" semantic space: as the unbounded write channel grows, the parametric/contextual duality becomes a matter of degree rather than kind, empirically confirming the geometric prediction that the full d-dimensional space is the union of both channels.
- OUT context-write-unbounded-complement — The context window functions as the unbounded write channel that complements the rank-one parametric write: where parametric editing is confined to a single MLP's addressable subspace, the context channel injects arbitrary quantities of verified knowledge, making the two write channels capacity-complementary rather than redundant.
- OUT knowledge-routing-as-geometric-gate — The parametric/contextual knowledge routing is a geometric gate based on subspace membership rather than a statistical frequency heuristic: the model routes to parametric recall when the fact direction lies within the rank-one addressable subspace, and to contextual retrieval when it does not, with the faithfulness validation (accuracy scaling with document relevance) as the empirical confirmation that the gate responds to geometry, not statistics.
- OUT parametric-write-subspace-boundary — The operational boundary between parametric recall and contextual retrieval is precisely the geometric boundary of the rank-one addressable subspace: facts whose subject-key projection aligns with the locally-stored key covariance are parametrically editable, while facts outside this subspace must be externally supplied.
- OUT scoped-factual-knowledge-lifecycle — For single-hop factual (entity-relation-object) knowledge specifically, the full lifecycle—distributed corpus acquisition → local MLP key-value storage → parametric recall → contextual supplementation → rank-one correction—forms a coherent, validated closed loop in which each stage is geometrically well-defined and operationally distinct.