The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
High-recall deep learning: A gated recurrent unit approach to bank account fraud detection on imbalanced data
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Entity embeddings reach AUC-ROC 0.9612 on IEEE-CIS fraud data, statistically tied with CatBoost and superior to tier group encoding (0.9548), with CatBoost leading on AUC-PR.
citing papers explorer
-
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
-
Interpretable vs Learned Encoders for High-Cardinality Fraud Detection
Entity embeddings reach AUC-ROC 0.9612 on IEEE-CIS fraud data, statistically tied with CatBoost and superior to tier group encoding (0.9548), with CatBoost leading on AUC-PR.