Routing Strategies & Feature Modeling

Cost-Aware Routing Strategies & Models

The routing engine extracts 54 computationally inexpensive features prior to invoking any LLM:

OCR Confidence Metrics: Mean confidence, minimum token confidence, standard deviation, count of low-confidence tokens (<80%, <50%).
Lexical & Linguistic Features: Out-of-vocabulary (OOV) ratio against historical lexicon, archaic character frequency (e.g. ſ, œ, ligature anomalies).
Statistical Text Metrics: Punctuation density, digit-to-letter ratios, average word length, uppercase token anomalies.
Layout Context: Bounding box coordinates, line height variance, bounding box density.

The router was benchmarked across multiple learning paradigms:

Lasso Regression (L1): Sparse feature selection, highly interpretable, <0.1s inference time on single CPU core.
Ridge Regression (L2): Smooth shrinkage across correlated confidence features.
Support Vector Machines (SVM): Non-linear RBF kernel separating degradation clusters.
Multi-Layer Perceptron (NN): 2-layer feedforward network predicting expected CER reduction.
ConfBERT: Fine-tuned lightweight language model scoring token perplexity and error likelihood.

Selective Efficiency: At \tau = 0, the Lasso router skips 40.2% of segments, reducing API costs by 38.5% while degrading final CER by only 0.20 percentage points (3.12% vs 2.92%).
Oracle Tracking: The regression router achieves 91.4\% of the theoretical maximum gain achievable by an omniscient oracle.

Figure 1: Cost vs accuracy trade-off curves for regression routing across prompt regimes.

Figure 2: Optimal confidence threshold cutoffs minimizing inference cost while maximizing CER delta.