LoGo: Token-Level Dynamic Local-Global Attention
Not assessedPlan blockedFindingclaim-long-range-recall
LoGo reports higher average needle-style RULER recall than the three comparison paradigms at both the 32k and 128k context-extension stages, with averages of 83.0 and 65.4 percentage points.
Source: paper-fixed:Section 4.2 and Table 4, p. 7
Reported and observed measurements
ruler_average
m-table4-logo-ruler-32k
Reported 83 percentage_points
Observed — percentage_points
ruler_average
m-table4-logo-ruler-128k
Reported 65.4 percentage_points
Observed — percentage_points
Assessments (0)
No immutable Assessment has been published for this Claim yet.
Runs (0)
No execution has been linked to this Claim yet.