LoRA modules are a complementary, finite-capacity parametric memory for LLMs: capacity grows with rank, small ranks are most parameter-efficient, synthetic QA data helps most, and practical multi-LoRA systems are bottlenecked by routing and merging degradation.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Profile Drift Detection measures changes in partial dependence profiles with new metrics to detect concept drift while providing explanations and supporting efficient MLOps monitoring.
citing papers explorer
-
Understanding LoRA as Knowledge Memory: An Empirical Analysis
LoRA modules are a complementary, finite-capacity parametric memory for LLMs: capacity grows with rank, small ranks are most parameter-efficient, synthetic QA data helps most, and practical multi-LoRA systems are bottlenecked by routing and merging degradation.
-
From XAI to MLOps: Explainable Concept Drift Detection with Profile Drift Detection
Profile Drift Detection measures changes in partial dependence profiles with new metrics to detect concept drift while providing explanations and supporting efficient MLOps monitoring.